tools_list stringlengths 173 352k | messages_history stringlengths 195 9.15k | binary_label stringclasses 2
values | label stringclasses 4
values | failure_reason stringclasses 632
values |
|---|---|---|---|---|
["{'type': 'function', 'function': {'name': 'get_timeline_summary', 'description': '\\n Get a timeline summary of posts/drops, optionally within a date range.\\n\\n Args:\\n start_date: Optional start date in YYYY-MM-DD format\\n end_date: Optional end date in YYYY-MM-DD format\\n ', 'parameters'... | [
{"role": "system", "content": "You are a helpful assistant with access to several tools. Use these tools to respond to user requests effectively.
**Available Tools:**
- `get_timeline_summary()`: Summarizes recent activity or events in a user's timeline. Use when a user asks for a general overview or highlights... | INCORRECT | PARAM_VALUE_ERROR | ['The 'post_id' in the incorrect parameters ('post_78902') is off by one digit and does not match the 'post ID 78901' explicitly mentioned in the user's query.'] |
["{'name': 'search_people', 'inputSchema': {'type': 'object', 'required': ['query'], 'properties': {'limit': {'type': 'integer', 'title': 'Limit', 'default': 5}, 'query': {'type': 'string', 'title': 'Query'}, 'timeout': {'type': 'integer', 'title': 'Timeout', 'default': 1800}, 'search_type': {'type': 'string', 'title':... | [
{"role": "system", "content": "You have access to a tool named `search_people`. Use this tool to find information about individuals. `search_people` requires the following parameters:
- `first_name` (string, optional): The first name of the person to search for.
- ``last_name` (string, optional): The last name of... | INCORRECT | PARAM_VALUE_ERROR | ['The user query explicitly mentions 'Tech Innovations', but the 'company' parameter in the incorrect tool call is set to 'Tech Innovationns', which contains a subtle typo (an extra 'n') at the end of 'Innovations'.'] |
["{'type': 'function', 'function': {'name': 'fetch_reddit_post_content', 'description': '\\n Fetch detailed content of a specific post\\n \\n Args:\\n post_id: Reddit post ID\\n comment_limit: Number of top level comments to fetch\\n comment_depth: Maximum depth of comment tree to traverse... | [
{
"role": "user",
"content": "Can you tell me Chainlink's revenue for the first quarter of 2023?"
},
{
"type": "function_call",
"id": "call_b51u0t4q1zw8s6jp1",
"name": "get_chainlink_revenue",
"arguments": {'start_date': '2023-01-01', 'end_date': '2023-... | INCORRECT | PARAM_VALUE_ERROR | ['The user requested revenue for the *first quarter* of 2023, which typically ends on March 31st. The 'end_date' provided ('2023-03-30') is one day short of the full quarter, subtly altering the requested time frame.'] |
["{'name': 'get_network_requests', 'description': 'Get network requests from the currently open browser page.\\n\\nArgs:\\n last_n: Number of network request entries to return, prioritizing the most recent ones.\\n Use a large number to get all requests.\\n\\nReturns:\\n A list of network request entrie... | [
{"role": "system", "content": "You are a security operations assistant with access to several specialized tools. Use these tools to respond to user queries effectively.
Tools available:
- `list_recent_assets()`: Use this tool to retrieve a list of recently added or modified assets. Useful when a user asks about... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'name': 'get_build_status', 'description': 'Get build status\\n\\n Args:\\n job_name: Name of the job\\n build_number: Build number to check, defaults to latest\\n\\n Returns:\\n Build information dictionary\\n ', 'inputSchema': {'type': 'object', 'title': 'get_build_statusArguments', '... | [
{
"role": "user",
"content": "Could you please create a new folder named 'weekly_summaries' inside my 'reports' directory? The 'reports' directory is located under '/users/downloads'."
},
{
"type": "function_call",
"id": "call_38f88ttndaewhxgn0rajkf7ltrol",
"na... | INCORRECT | PARAM_VALUE_ERROR | ['The 'sub_directory_name' in the incorrect parameters is 'weekly_summary' (singular), which subtly differs from the user's explicit request for 'weekly_summaries' (plural).'] |
["{'type': 'function', 'function': {'name': 'create_prediction', 'description': 'Generate an prediction from a text prompt using Flux Schnell model', 'parameters': {'properties': {'seed': {'type': 'integer', 'description': 'Random seed. Set for reproducible generation'}, 'prompt': {'type': 'string', 'minLength': 1, 'de... | [
{
"role": "user",
"content": "Please generate a single, hyperrealistic image of a majestic lion in a savanna at sunset, with dramatic cinematic lighting. Use the `stable-diffusion-xl-1.0` model and make the output a square, 1024x1024 pixel image."
},
{
"type": "function_call",... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly requested a 'single image', but the `num_outputs` parameter in the tool call was incorrectly set to '2'.'] |
["{'type': 'function', 'function': {'name': 'greet', 'description': 'Greet a user by name.', 'parameters': {'properties': {'name': {'type': 'string', 'title': 'Name'}}, 'required': ['name']}}}"] | [
{"role": "system", "content": "You have access to a `greet` tool. This tool is designed to send a greeting to a specified person. You should use the `greet` tool when the user explicitly asks you to greet someone by name. The `greet` tool requires a single parameter: `name`, which should be the name of the indivi... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly requested to greet 'Alice'. The incorrect parameters substitute 'Alice' with 'Alicia', which is a one-letter difference that changes the intended recipient of the greeting.'] |
["{'type': 'function', 'function': {'name': 'busca_cep', 'description': 'Busca o cep de um cliente', 'parameters': {'properties': {'cep': {'type': 'string', 'description': 'Número do CEP'}}, 'required': ['cep']}}}"] | [
{"role": "system", "content": "Você tem acesso à ferramenta `busca_cep`. Esta ferramenta permite que você obtenha detalhes de endereço (rua, bairro, cidade, estado) a partir de um Código de Endereçamento Postal (CEP) brasileiro. Utilize esta ferramenta sempre que o usuário fornecer um CEP e solicitar informações ... | INCORRECT | PARAM_VALUE_ERROR | ['Os parâmetros incorretos contêm o CEP '01001-001', que difere em um único dígito (o último '1' em vez de '0') do CEP '01001-000' solicitado explicitamente pelo usuário na query. Este é um erro sutil que resultaria na busca de um endereço diferente.'] |
["{'name': 'search_crypto', 'description': '\\n Search for coins, categories and markets.\\n\\n Args:\\n query: Search query string\\n ', 'inputSchema': {'type': 'object', 'title': 'search_cryptoArguments', 'required': ['query'], 'properties': {'query': {'type': 'string', 'title': 'Query'}}}}", '{\'type... | [
{"role": "system", "content": "You are an AI assistant capable of interacting with various tools to provide information about cryptocurrencies and Farcaster social network casts.
- Use `search_crypto(query: str)` to find cryptocurrencies by their name or symbol. Call this tool when a user is looking for a specif... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly requested 'the first 10 cryptocurrencies', but the 'limit' parameter was incorrectly set to '1' instead of '10', which would only retrieve a single coin.'] |
['{\'name\': \'issue_get_comments\', \'description\': \'Get comments of a Yandex Tracker issue by its id\', \'inputSchema\': {\'type\': \'object\', \'title\': \'issue_get_commentsArguments\', \'required\': [\'issue_id\'], \'properties\': {\'issue_id\': {\'type\': \'string\', \'title\': \'Issue Id\', \'description\': "I... | [
{
"role": "user",
"content": "Could you please retrieve all comments associated with the Yandex Tracker issue TICKET-5678?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id":... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
['{\'type\': \'function\', \'function\': {\'name\': \'budget_summary\', \'description\': \'Get a summary of the budget for a specific month highlighting overspent categories that need attention and categories with a positive balance that are doing well.\', \'parameters\': {\'properties\': {\'month\': {\'type\': \'strin... | [
{
"role": "user",
"content": "I spent $45.50 on lunch at Pizzeria with Sarah today, November 1st. Please record it as dining out."
},
{
"type": "function_call",
"id": "call_33zgr",
"name": "create_transaction",
"arguments": {'amount': 45.05, 'category':... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly stated 'I spent $45.50' and mentioned the date 'November 1st'. The incorrect parameters show an amount of '45.05' (a subtle number difference) and a date of '2023-11-02' (off by one day). These values contradict the user's clear input.'] |
["{'type': 'function', 'function': {'name': 'list_websites', 'description': 'List known websites with llms.txt files', 'parameters': {'properties': {'filter_llms_txt': {'type': 'boolean', 'description': 'Only show websites with llms.txt'}, 'filter_llms_full_txt': {'type': 'boolean', 'description': 'Only show websites w... | [
{"role": "system", "content": "You are a helpful assistant that can search for books. You have access to tools to search for books by author or by title. When a user asks to find books by an author, use the `author_search` tool. When a user asks to find a specific book by its title, use the `book_search` tool."},... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'type': 'function', 'function': {'name': 'slack_add_reaction', 'description': 'Add a reaction emoji to a message', 'parameters': {'properties': {'reaction': {'type': 'string', 'description': 'The name of the emoji reaction (without ::)'}, 'timestamp': {'type': 'string', 'description': 'The timestamp of the message t... | [
{"role": "system", "content": "You are a helpful Slack assistant. You have access to a set of tools to interact with Slack.
* `slack_add_reaction(channel: str, timestamp: str, name: str)`: Use this to add an emoji reaction to a specific message. `channel` is the ID of the channel, `timestamp` is the `ts` of the... | INCORRECT | PARAM_VALUE_ERROR | ['The 'parent_message_ts' parameter is incorrect. The user explicitly provided '1678886400.123456', but the parameter value is '1678886400.123455', differing by a single digit at the end. This subtle change would target the wrong parent message.'] |
["{'name': 'search_meal', 'description': '\\n Search for a meal by name and return cooking instructions.\\n ', 'inputSchema': {'type': 'object', 'title': 'search_mealArguments', 'required': ['meal_name'], 'properties': {'meal_name': {'type': 'string', 'title': 'Meal Name'}}}}", "{'name': 'web_search_exa', 'descri... | [
{"role": "system", "content": "You are an AI assistant with access to tools to help users with their meal-related queries.
Available tools:
- `search_meal(meal_name: str, cuisine: str)`: Use this tool to find detailed information about a specific meal, including ingredients and preparation instructions. Require... | INCORRECT | PARAM_VALUE_ERROR | ['The 'meal_name' parameter has a one-letter typo ('Massala' instead of 'Masala'), which subtly changes the spelling of the meal name compared to the user's explicit request.'] |
['{\'name\': \'get_brand_info_and_logo\', \'description\': \'Fetch brand information (logos, colors, etc.) for a given domain using the Brandfetch API.\', \'inputSchema\': {\'type\': \'object\', \'required\': [\'domain\'], \'properties\': {\'domain\': {\'type\': \'string\', \'description\': \'Domain name to fetch brand... | [
{"role": "system", "content": "You are a highly capable AI assistant with access to a suite of specialized tools. Your primary goal is to accurately understand user requests and leverage the appropriate tools to fulfill them.
Here are the tools at your disposal and how to use them:
1. `get_brand_info_and_logo(... | INCORRECT | PARAM_VALUE_ERROR | ['The 'brand_name' parameter in the incorrect call is 'Tech Innovators Corp.' instead of 'Tech Innovators Inc.', which is a subtle one-word difference. Additionally, 'include_logo' is set to 'false' and 'logo_size' to 'medium', directly contradicting the user's request for 'their large-sized logo'.'] |
["{'name': 'vehicle', 'description': 'Get a details of a vehicle by id', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Vehicle id'}}, 'additionalProperties': False}}", "{'type': 'function', 'function': ... | [
{"role": "system", "content": "You are an AI assistant designed to help users find research papers and surveys. You have access to the following tool:
- `arvix_survey(query: str, max_results: int)`: Use this tool to search for research papers and survey articles on ArXiv. The 'query' parameter accepts keywords re... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'name': 'get_network_requests', 'description': 'Get network requests from the currently open browser page.\\n\\nArgs:\\n last_n: Number of network request entries to return, prioritizing the most recent ones.\\n Use a large number to get all requests.\\n\\nReturns:\\n A list of network request entrie... | [
{"role": "system", "content": "You are an AI assistant capable of interacting with a web browser to assist users. You have access to the following tools:
1. `get_network_requests(url_pattern: str = None, method: str = None, status_code_range: str = None, request_types: list = None, headers: dict = None, payload_... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly asked for requests to the `/api/v2/orders` endpoint (plural), but the `url_pattern` in the incorrect parameters is `*/api/v2/order` (singular), which is a 1-letter difference that would lead to filtering the wrong URL.'] |
["{'name': 'fetch-multilingual-docs', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['packageName', 'languages'], 'properties': {'languages': {'type': 'array', 'items': {'type': 'string'}, 'description': 'List of programming languages or repository types to check (e... | [
{
"role": "user",
"content": "Can you provide a historical price analysis for Ethereum (ETH) over the past 10 days, with a 6-hour interval?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'type': 'function', 'function': {'name': 'SpotifySearch', 'description': 'Search for tracks, albums, artists, or playlists on Spotify.', 'parameters': {'properties': {'limit': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Limit', 'default': 10, 'description': 'Maximum number of items to return'}, 'qty... | [
{
"role": "user",
"content": "Please add 'Blinding Lights' by The Weeknd to my Spotify queue."
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
"stop_rea... | INCORRECT | PARAM_VALUE_ERROR | ['The user requested 'Blinding Lights' by The Weeknd, which corresponds to the track ID '3rRkhqWk9t2b6F9yB912gS'. The incorrect parameter '3rRkhqWk9t2b6F9yB912gT' has a subtle one-character difference ('S' changed to 'T') at the end. This slight alteration makes it an invalid or incorrect ID for the requested song, pot... |
["{'name': 'get-crypto-price', 'description': 'Get current price and 24h stats for a cryptocurrency', 'inputSchema': {'type': 'object', 'required': ['symbol'], 'properties': {'symbol': {'type': 'string', 'description': 'Cryptocurrency symbol (e.g., BTC, ETH)'}}}}", "{'name': 'get-market-analysis', 'description': 'Get d... | [
{
"role": "user",
"content": "Could you provide me with a daily market analysis for Bitcoin against the US Dollar?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
... | INCORRECT | PARAM_VALUE_ERROR | ['The 'currency_pair' in the incorrect parameters is 'BTC/US', which is subtly different from the requested 'BTC/USD' (Bitcoin against the US Dollar). The user explicitly asked for 'US Dollar', implying 'USD', not the partial 'US'.'] |
["{'name': 'handle_payment_flow', 'description': '\\n Handle the payment flow for orders.\\n \\n Args:\\n data: Dictionary containing data for the payment flow\\n - dining_option: The selected dining option (dinein/takeout)\\n - order_tag_number: The order tag number for dine-in or... | [
{"role": "system", "content": "You are an AI assistant with access to a set of tools to help users.
Available tools:
1. `verify_betha_token(token_id: str, user_id: str)`: This tool is used to verify the authenticity and validity of a Bēthā API token for a specific user. Call this tool when a user explicitly as... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
['{\'name\': \'getAlerts\', \'description\': \'Get current alerts for national parks including closures, hazards, and important information\', \'inputSchema\': {\'type\': \'object\', \'$schema\': \'http://json-schema.org/draft-07/schema#\', \'properties\': {\'q\': {\'type\': \'string\', \'description\': \'Search term t... | [
{
"role": "user",
"content": "Are there any current closures in Yellowstone National Park?"
},
{
"type": "function_call",
"id": "call_0w5m4saiy",
"name": "getAlerts",
"arguments": {'parkCode': 'YEL', 'type': 'closure'}
}
] | INCORRECT | PARAM_VALUE_ERROR | ['The 'parkCode' 'YEL' is subtly incorrect. The user explicitly asked about 'Yellowstone National Park', which has the official park code 'YELL'. The provided 'YEL' is missing one 'L', making it an invalid or unrecognized park code for Yellowstone.'] |
['{\'type\': \'function\', \'function\': {\'name\': \'get_n8n_info\', \'description\': \'\\n Search the latest n8n resources for a given query.\\n \\n Args:\\n query: The query to search for (e.g. "HTTP Request node")\\n resource_type: The resource type to search in (docs, workflows, community)\\n - docs:... | [
{"role": "system", "content": "You are an assistant with access to tools. Your primary tool is `get_n8n_info`, which can retrieve various details about your n8n instance. Use `get_n8n_info` when the user asks for information about n8n workflows, executions, credentials, or other related components. You must speci... | INCORRECT | PARAM_VALUE_ERROR | ['The 'status' parameter in the incorrect call contains a subtle typo, 'activ', which should be 'active' to correctly filter for active workflows as requested by the user.'] |
["{'type': 'function', 'function': {'name': 'generate_image', 'description': 'Generate an image from a text prompt using Flux model', 'parameters': {'properties': {'width': {'type': 'integer', 'maximum': 1024, 'description': 'Width of the generated image', 'exclusiveMinimum': 0}, 'height': {'type': 'integer', 'maximum'... | [
{"role": "system", "content": "You are a helpful assistant with access to several tools. You should use these tools to fulfill user requests.
Available tools:
- `play_video(video_id: str)`: Use this tool to play a specific video given its unique video ID.
- `call_director(director_name: str, movie_title: str)`... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
["{'type': 'function', 'function': {'name': 'update_rule', 'description': 'Update an existing policy rule', 'parameters': {'properties': {'rule_data': {'type': 'object', 'description': 'Updated rule configuration data'}, 'rule_name': {'type': 'string', 'description': 'Name of the rule to update'}, 'rule_type': {'type':... | [
{"role": "system", "content": "You are a helpful assistant with access to tools for interacting with a log management system.
- `get_label_values(label_name: str)`: Use this tool to retrieve all unique values for a specific log label. This is useful for exploring available labels and their possible values before ... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'type': 'function', 'function': {'name': 'basic_query_syntax', 'description': '', 'parameters': {'properties': {}, 'required': []}}}", "{'type': 'function', 'function': {'name': 'advanced_query_syntax', 'description': '', 'parameters': {'properties': {}, 'required': []}}}", "{'name': 'endpoint_schema', 'description'... | [
{
"role": "user",
"content": "Can you find the 10 most recent financial reports for me?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_n5uisvbk2k3j6k4mb440drg0ntin... | INCORRECT | PARAM_VALUE_ERROR | ['The user specifically requested 'the 10 most recent' reports, but the incorrect tool call sets the 'limit' parameter to '11', asking for one more report than specified.'] |
['{\'name\': \'start_new_session\', \'description\': \'Start a new browser session. Provide an instruction like "Go to https://example.com" or "Search for products on Amazon". Returns executionId for the session and initial page data with interactive elements and HTML markup.\', \'inputSchema\': {\'type\': \'object\', ... | [
{"role": "system", "content": "You are an assistant capable of interacting with a CI/CD system. You have access to the following tools:
- `get_build_status(build_id: str)`: Use this tool to retrieve the current status of a specific software build. Call this when the user asks for the status or progress of a build... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'type': 'function', 'function': {'name': 'taskComplete', 'description': 'Complete a task in a project', 'parameters': {'properties': {'taskId': {'type': 'string'}, 'projectId': {'type': 'string'}}, 'required': ['projectId', 'taskId']}}}", "{'name': 'taskCreate', 'description': 'Create one or more tasks in a project'... | [
{"role": "system", "content": "You are an assistant with access to the 'send_webhook' tool. Use this tool to send HTTP POST requests to specified URLs. The 'send_webhook' tool requires a 'url' parameter (string) for the target endpoint and an optional 'data' parameter (string or JSON object) containing the payloa... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
["{'type': 'function', 'function': {'name': 'get_emergency_contacts', 'description': 'Retrieves emergency contact information for a specific location', 'parameters': {'properties': {'location': {'type': 'string', 'description': 'Location to get emergency contacts for'}, 'serviceType': {'type': 'array', 'items': {'type'... | [
{"role": "system", "content": "You are a helpful assistant designed to interact with various tools to fulfill user requests. Carefully analyze the user's intent to determine which tool, if any, is appropriate.
Available tools:
- `search_movie(query: str)`: Searches for a movie based on a title or keyword.
- `ge... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
['{\'name\': \'get_docs\', \'description\': \'\\n Search the latest docs for a given query and library.\\n Supports langchain, openai, and llama-index.\\n\\n Args:\\n query: The query to search for (e.g. "Chroma DB")\\n library: The library to search in (e.g. "langchain")\\n\\n Returns:\\n Text from the do... | [
{
"role": "user",
"content": "Could you help me find the documentation on how to generate invoices within our Billing System?"
},
{
"type": "function_call",
"id": "call_3gt0akrzgm02julex1p81q",
"name": "get_docs",
"arguments": {'product': 'Billing Syste... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly asked for documentation related to the 'Billing System' (singular) and the process of 'invoice generation'. The incorrect parameters use 'Billing Systems' (plural) for the product and 'invoice generating' (present participle) for the query, which are subtle linguistic mismatches that could lead to... |
["{'name': 'get_articles_for_topic', 'description': 'On a given topic, get evidence-based medical articles and information from patient.info (highly trusted by doctors, up-to-date medical resource).', 'inputSchema': {'type': 'object', 'required': ['topic'], 'properties': {'topic': {'type': 'string', 'description': 'Top... | [
{"role": "system", "content": "You are an AI assistant with the ability to convert PDF documents into Markdown format. When a user requests to convert a PDF, you should use the `pdf_to_markdown` tool. This tool requires a `pdf_url` parameter, which is the direct URL to the PDF file you want to convert. Ensure the... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
["{'name': 'city-locator', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['city', 'stateAbbreviation', 'country'], 'properties': {'city': {'type': 'string'}, 'country': {'type': 'string'}, 'stateAbbreviation': {'type': 'string'}}, 'additionalProperties': False}}", "... | [
{"role": "system", "content": "You are an AI assistant designed to help users with project and geographical information. You have access to the following tools:
1. city-locator(city_name: str): Use this tool to find geographical details, population, or other relevant information about a specific city. Call this... | INCORRECT | PARAM_VALUE_ERROR | ['The user requested a 'brief overview' which correctly maps to 'high-level' for the detail_level parameter. However, the incorrect parameters provided 'hi-level', which is a subtle one-letter typo and does not match the expected enumeration for the detail_level parameter.'] |
["{'type': 'function', 'function': {'name': 'get_asset_price', 'description': 'Retrieves current pricing information for various assets including precious metals and cryptocurrencies', 'parameters': {'properties': {'random_string': {'type': 'string', 'description': 'Dummy parameter for no-parameter tools'}}, 'required'... | [
{
"role": "user",
"content": "What's the current trading price for Bitcoin?"
},
{
"id": "call_7m0kr3ieu5t3y46pbzw419w2",
"type": "function",
"function": {
"name": "get_asset_price",
"arguments": {'asset_name': 'Bitcoins'}
}
}... | INCORRECT | PARAM_VALUE_ERROR | ['The user query specifically asks for 'Bitcoin' (singular), but the incorrect parameter uses 'Bitcoins' (plural). This subtle difference could lead to an invalid asset lookup or no data found if the system expects the exact singular name.'] |
['{\'name\': \'get_kline\', \'description\': \'\\n Get K-line (candlestick) data\\n\\n Args:\\n category (str): Category (spot, linear, inverse, etc.)\\n symbol (str): Symbol (e.g., BTCUSDT)\\n interval (str): Time interval (1, 3, 5, 15, 30, 60, 120, 240, 360, 720, D, W, M)\\n start (O... | [
{
"role": "user",
"content": "Can you fetch my 15 most recent open orders in the linear category for ETHPERP?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'name': 'get_label_values', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['label'], 'properties': {'label': {'type': 'string', 'description': 'Label name to get values for'}}, 'additionalProperties': False}}", '{\'name\': \'query_loki\', \'inputSchema\': {\'type... | [
{"role": "system", "content": "You are a helpful assistant with access to several specialized tools. Use these tools to answer user queries effectively and accurately.
Available tools:
- `get_label_values(label_name: str)`: Use this tool to retrieve all possible values for a given label in a monitoring system. U... | INCORRECT | PARAM_VALUE_ERROR | ['The 'time_period' parameter is misspelled as 'todday' instead of 'today'. This subtle typo would prevent the tool from recognizing the correct time period for the horoscope.'] |
["{'type': 'function', 'function': {'name': 'get_package_stats', 'description': '', 'parameters': {'properties': {'package_name': {'type': 'string', 'title': 'Package Name'}}, 'required': ['package_name']}}}", "{'type': 'function', 'function': {'name': 'get_package_releases', 'description': '', 'parameters': {'properti... | [
{"role": "system", "content": "You are an AI assistant capable of interacting with a package management system. You have access to the following tools:
- `search_packages(query: str, limit: int = 10)`: Searches for packages based on a query string. Use this when the user wants to find packages by name or keyword... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly requested 'the top 5 results', but the 'limit' parameter in the incorrect tool call is set to '4', which would return fewer results than specified by the user.'] |
["{'name': 'search-news', 'description': 'Search for news articles from The Verge by keyword', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['keyword'], 'properties': {'days': {'type': 'number', 'description': 'Number of days to look back (default: 30)'}, 'keyword'... | [
{"role": "system", "content": "You are a helpful assistant with access to several specialized tools. Use these tools to answer user queries effectively.
Here are the tools you can use:
- **search-news(query: string)**: Use this tool to find current news articles, headlines, or recent events related to a specific... | INCORRECT | PARAM_VALUE_ERROR | ['The 'language' parameter in 'incorrect_tool_call_1_params' uses 'fre' which is an ISO 639-2/3 code, but the tool expects an ISO 639-1 two-letter code like 'fr'.'] |
["{'name': 'human-messages-prompts', 'description': 'Generate a prompt for a human message', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['platform'], 'properties': {'message': {'type': 'string'}, 'platform': {'enum': ['twitter', 'discord', 'telegram', 'whatsapp',... | [
{
"role": "user",
"content": "Can you show me some examples of system prompts specifically tailored for data analysis tasks?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id... | INCORRECT | PARAM_VALUE_ERROR | ['The 'prompt_category' parameter was incorrectly changed from 'system' to 'systems'. The user specifically asked for 'system prompts' (singular), implying a category named 'system', not 'systems'.'] |
["{'name': 'get_adset_by_id', 'description': '$2a', 'inputSchema': {'type': 'object', 'title': 'get_adset_by_idArguments', 'required': ['adset_id'], 'properties': {'fields': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'title': 'Fields', 'default': None}, 'adset_id': {'type': 'string', ... | [
{"role": "system", "content": "You are an AI assistant designed to help users manage and retrieve information from a knowledge base. You have access to the following tools:
1. `get_definitions(term: str)`: Use this tool to retrieve the definition of a specific term or concept. Call this when the user explicitly ... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'name': 'create_scheduled_email_send_at_specific_time', 'description': '$20', 'inputSchema': {'type': 'object', 'title': 'create_scheduled_email_send_at_specific_timeArguments', 'required': ['title', 'subject', 'body', 'minutes', 'hours', 'mdays', 'months', 'wdays'], 'properties': {'body': {'type': 'string', 'title'... | [
{"role": "system", "content": "You are an email scheduling assistant. Your primary function is to manage scheduled emails.
- Use the 'create_scheduled_email_send_at_specific_time' tool to compose and schedule an email for a future date and time. This tool requires the recipient's email address, the subject line,... | INCORRECT | PARAM_VALUE_ERROR | ['The 'recipient_email' parameter contains a subtle, one-letter typo ('alica.smith@example.com' instead of 'alice.smith@example.com'). This does not precisely match the recipient's email address specified in the user's query.'] |
["{'name': 'check_deep_research_status', 'description': 'Check the status of an ongoing deep research job.', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['job_id'], 'properties': {'job_id': {'type': 'string', 'description': 'The job ID to check status for'}}, 'add... | [
{"role": "system", "content": "You are an AI assistant capable of interacting with various tools to assist users with their requests.
- `check_deep_research_status(research_id: str)`: Use this tool to check the current status of a previously initiated deep research task. Requires the `research_id` returned when t... | INCORRECT | PARAM_VALUE_ERROR | ['The `research_goals` parameter contains a subtle misspelling: 'philanthrophic' instead of 'philanthropic'. This single letter difference ('ph' vs 'p' before 'ropic') makes the parameter value technically incorrect compared to the user's precise request.'] |
['{\'name\': \'getLifelogs\', \'description\': \'Retrieve lifelog entries from your Limitless AI pendant. Access your recorded conversations, thoughts, and daily activities with flexible filtering options.\', \'inputSchema\': {\'type\': \'object\', \'$schema\': \'http://json-schema.org/draft-07/schema#\', \'properties\... | [
{"role": "system", "content": "You are an AI assistant designed to help users manage their lifelog entries. You have access to the following tools:
1. `getLifelogs(start_date: str, end_date: str, category: str = null)`: Retrieves a list of lifelog entries within a specified date range, optionally filtered by cate... | INCORRECT | PARAM_VALUE_ERROR | ['The user requested entries for 'January 2023', which implies the end date should be '2023-01-31', not '2023-01-30'. Furthermore, the category 'wok' is a subtle typo for 'work' and would likely result in incorrect filtering.'] |
["{'type': 'function', 'function': {'name': 'qrcode', 'description': 'Generate a QR code image', 'parameters': {'properties': {'size': {'type': 'number', 'default': 256, 'description': 'The size of qrcode, default is 256'}, 'text': {'type': 'string', 'description': 'The input string to generate qrcode'}, 'margin': {'ty... | [
{"role": "system", "content": "You are an AI assistant designed to help manage a wiki. You have access to tools that allow you to interact with wiki pages and files. You can retrieve information about the history of a page, get the current content of a page, retrieve details about a file, create new pages, update... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'type': 'function', 'function': {'name': 'generateImage', 'description': 'Generate images using the 4o-image API and automatically open the results in your browser.\\n\\nThis tool generates images based on your prompt and automatically opens them in your default browser, while also returning a clickable link.\\n\\nT... | [
{
"role": "user",
"content": "Hey, can you whip up an image for me? I'm thinking of a futuristic city scene at sunset, with some cool flying cars and really tall buildings. Make it in a cyberpunk style, and a square image would be great."
},
{
"role": "assistant",
"sto... | INCORRECT | PARAM_VALUE_ERROR | ['The 'size' parameter '1024x10224' contains an extra digit in the height dimension (10224 instead of 1024), making it an invalid image size format and not aligning with the user's request for a 'square image'.'] |
['{\'name\': \'get-rounds\', \'description\': \'Get all rounds data from OnSecurity from client in a high level summary. When replying, only include the summary, not the raw data and be sure to present the data in a way that is easy to understand for the client. Rounds can be pentest rounds, scan rounds, or radar round... | [
{
"role": "user",
"content": "Could you please show me the top 5 most critical findings from pentest round 9876?"
},
{
"id": "call_6dmbwz8xdkkmh66szbyuxsn",
"type": "function",
"function": {
"name": "get-findings",
"arguments": {'limit':... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
['{\'name\': \'get-channel-casts\', \'description\': \'Get casts from a specific Farcaster channel\', \'inputSchema\': {\'type\': \'object\', \'$schema\': \'http://json-schema.org/draft-07/schema#\', \'required\': [\'channel\'], \'properties\': {\'limit\': {\'type\': \'number\', \'description\': \'Maximum number of cas... | [
{
"role": "user",
"content": "Can you show me the recent posts from Farcaster user ID 3?"
},
{
"type": "function_call",
"id": "call_3euw95bk",
"name": "get-user-casts",
"arguments": {'user_id': '8'}
}
] | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly requested casts from Farcaster user ID '3', but the incorrect parameters specify user ID '8'. This is a one-number difference, leading to fetching casts for a completely different user than intended by the user's query.'] |
["{'type': 'function', 'function': {'name': 'get_players', 'description': 'Gets the list of players from one of the following leagues NBA, MLB, NFL', 'parameters': {'properties': {'cursor': {'type': 'number', 'description': 'Cursor for pagination, the value should be next_cursor from previous call of get_players tool, ... | [
{
"role": "user",
"content": "What games did the Los Angeles Lakers play on October 26th, 2023?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_aspent79v4i84j7qdi6"... | INCORRECT | PARAM_VALUE_ERROR | ['The 'date' parameter '2023-10-27' is one day off from the requested 'October 26th, 2023'. Additionally, the 'team_id' 'LA' is an incorrect abbreviation for the Los Angeles Lakers, which should be 'LAL', and 'LA' could ambiguously refer to multiple Los Angeles teams.'] |
["{'type': 'function', 'function': {'name': 'get_node', 'description': 'Get a specific node from a Figma file\\n\\n Args:\\n file_key (str): The file key found in the shared Figma URL, e.g. if url is https://www.figma.com/proto/do4pJqHwNwH1nBrrscu6Ld/Untitled?page-id=0%3A1&node-id=0-3&viewport=361%2C3... | [
{
"role": "user",
"content": "Can you give me the full details for node ID 12345?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_if61xi73ixuuvu6v6d1re8zbk",
... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly asked for 'node ID 12345', but the incorrect parameter `id` provides 'node_12346', which is an off-by-one error in the node identifier.'] |
["{'type': 'function', 'function': {'name': 'getLiveTemperature', 'description': '\\n Get live temperature for a specific location.\\n\\n Args:\\n latitude: The latitude coordinate (e.g., 40.7128 for New York)\\n longitude: The longitude coordinate (e.g., -74.0060 for New York)\\n\\n Returns:\\n ... | [
{"role": "system", "content": "You are an AI assistant capable of performing two main actions: retrieving code and speaking responses. Use the `get_code` tool when the user asks for programming code, scripts, or examples related to a specific task or language. Use the `speak_response` tool to generate an audio ou... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'name': 'sequentialthinking', 'description': '$1f', 'inputSchema': {'type': 'object', 'title': 'sequentialthinkingArguments', 'required': ['thought', 'thoughtNumber', 'totalThoughts', 'nextThoughtNeeded'], 'properties': {'thought': {'type': 'string', 'title': 'Thought'}, 'branchId': {'anyOf': [{'type': 'string'}, {'... | [
{"role": "system", "content": "You are an AI assistant designed to help users break down complex problems into manageable steps. You have access to a 'sequentialthinking' tool. Use this tool when the user asks for assistance in planning, organizing, or detailing a multi-step process or task. The 'sequentialthinki... | INCORRECT | PARAM_VALUE_ERROR | ['The 'objective' parameter in the incorrect tool call specifies 'Paris', but the user's query explicitly asks for a trip to 'London'. This is a one-word difference that completely changes the core subject of the request.'] |
["{'name': 'ip_lookup', 'description': 'Retrieve comprehensive information about an IP address, including geolocation, open ports, running services, SSL certificates, hostnames, and cloud provider details if available. Returns service banners and HTTP server information when present.', 'inputSchema': {'type': 'object',... | [
{"role": "system", "content": "You are a cybersecurity assistant with access to several specialized tools. Use these tools to provide accurate and relevant information based on user queries.
- `ip_lookup(ip_address: str)`: Use this to retrieve detailed information about a given IP address, such as its geographica... | INCORRECT | PARAM_VALUE_ERROR | ['The 'product_name' parameter has a subtle typo, 'Servar' instead of 'Server'. The correct spelling for the product name should be 'Apache HTTP Server' to match the user's query.'] |
["{'type': 'function', 'function': {'name': 'get_films', 'description': '', 'parameters': {'properties': {'name': {'type': 'string', 'title': 'Name'}}, 'required': ['name']}}}", "{'name': 'get_order', 'description': 'Get an order by ID', 'inputSchema': {'type': 'object', 'required': ['order_id'], 'properties': {'order_... | [
{
"role": "user",
"content": "I need to register a new webhook for my store 'st_1a2b3c'. The webhook URL is 'https://mydomain.com/webhooks/lemonsqueezy' and it should be triggered for the 'order_created' and 'subscription_payment_success' events. The secret key is 'a-very-secure-secret-string... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'type': 'function', 'function': {'name': 'get_sentry_issue', 'description': 'Get details for a specific Sentry issue using its ID or URL', 'parameters': {'properties': {'issue_id_or_url': {'type': 'string', 'description': 'The Sentry issue ID or the full URL of the issue page'}}, 'required': ['issue_id_or_url']}}}",... | [
{
"role": "user",
"content": "Can you fetch the complete details for event 1a2b3c4d5e6f7a8b9c0d1e2f3a4b5c6d in the 'frontend-app' project for 'my-company'?"
},
{
"type": "function_call",
"id": "call_zyeywb0",
"name": "get_event_details",
"arguments": {'... | INCORRECT | PARAM_VALUE_ERROR | ['The 'event_id' parameter in the incorrect tool call is '1a2b3c4d5e6f7a8b9c0d1e2f3a4b5c6e', which differs by one character ('e' instead of 'd' at the end) from the event ID '1a2b3c4d5e6f7a8b9c0d1e2f3a4b5c6d' explicitly mentioned in the user's query. This subtle change would lead to retrieving details for a different, ... |
["{'type': 'function', 'function': {'name': 'simulate_two_level_atom', 'description': 'Simulate dynamics of a two-level atom in an electromagnetic field', 'parameters': {'properties': {'detuning': {'type': 'number', 'description': 'Detuning from resonance in Hz'}, 'evolution_time': {'type': 'number', 'description': 'Ev... | [
{
"role": "user",
"content": "Can you show me the Rabi oscillations for an atom starting in the ground state, driven exactly on resonance with a Rabi frequency of 5 MHz, over a total simulation time of 10 microseconds?"
},
{
"id": "call_qur65yfejgcyqdrexb3m5v992",
"typ... | INCORRECT | PARAM_VALUE_ERROR | ['The 'initial_state' parameter is misspelled as 'gorund' instead of the correct 'ground'. This is a one-letter typo that makes the parameter invalid.'] |
["{'name': 'render-website-screenshot', 'description': 'Renders a screenshot of a website and returns it as an image or a JSON with the cache URL (preferred for full-page screenshots).', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['url'], 'properties': {'url': {'... | [
{
"role": "user",
"content": "Could you please grab a full-page screenshot of 'example.com' with a viewport of 1920 by 1080 pixels?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
... | INCORRECT | PARAM_VALUE_ERROR | ['The 'url' parameter is incorrect because the user specified 'example.com', but the parameter uses 'examples.com' (an added 's'). The 'width' parameter is also incorrect as the user requested '1920', but the parameter was set to '1921' (a single digit off).'] |
["{'name': 'search', 'description': '\\n Perform a search using SearXNG with all supported parameters.\\n ', 'inputSchema': {'type': 'object', 'title': 'searchArguments', 'required': ['q'], 'properties': {'q': {'type': 'string', 'title': 'Q'}, 'page': {'type': 'integer', 'title': 'Page', 'default': 1}, 'theme': {... | [
{"role": "system", "content": "You are an AI assistant designed to help users find relevant information. You have access to a tool named 'get_relevant_docs'. Use this tool when the user asks to retrieve documents, articles, or information related to a specific topic or keyword. The 'get_relevant_docs' tool requir... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
["{'type': 'function', 'function': {'name': 'basic_query_syntax', 'description': '', 'parameters': {'properties': {}, 'required': []}}}", "{'type': 'function', 'function': {'name': 'advanced_query_syntax', 'description': '', 'parameters': {'properties': {}, 'required': []}}}", "{'name': 'endpoint_schema', 'description'... | [
{"role": "system", "content": "You are an AI assistant with access to a file system management tool. Your primary function is to help users navigate and understand directory structures. You have access to the following tool:
- `get_deep_directory_tree(path: str, depth: int)`: This tool retrieves a detailed, multi... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'type': 'function', 'function': {'name': 'search_photos', 'description': 'Search for Unsplash photos', 'parameters': {'properties': {'page': {'type': 'number', 'default': 1, 'description': 'Page number (1-based)'}, 'color': {'type': 'string', 'description': 'Color filter (black_and_white, black, white, yellow, orang... | [
{
"role": "user",
"content": "I need to find the 5 latest black and white, landscape-oriented photos of dogs."
},
{
"id": "call_hp9lqrg0dn46azu4j8js",
"type": "function",
"function": {
"name": "search_photos",
"arguments": {'query': 'dog... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'type': 'function', 'function': {'name': 'get_financial_statement', 'description': 'Get the balance sheet of stock in The Securities Exchange of Thailand (SET).\\n\\n Args:\\n symbol (str): Stock symbol in The Securities Exchange of Thailand (SET).\\n from_year (int): The start YEAR of the financial... | [
{"role": "system", "content": "You are an AI assistant designed to help users retrieve specific information using a set of available tools. Your goal is to accurately interpret user requests and call the appropriate tool with the correct parameters.
Here are the tools you can use:
1. `get_financial_statement(c... | INCORRECT | PARAM_VALUE_ERROR | ['The user requested news for 'Bitcoin', which corresponds to the symbol 'BTC', not 'BTT'. Additionally, the user specifically asked for the 'five' most recent articles, but the 'limit' parameter was incorrectly set to 6, which is an off-by-one error.'] |
['{\'name\': \'retrieve_knowledge\', \'description\': \'Retrieves similar chunks from the knowledge base based on a query. Optionally, if a knowledge base is specified, only that one is searched; otherwise, all available knowledge bases are considered. By default, at most 10 documents are returned with a score below a ... | [
{
"role": "user",
"content": "What are the recommended guidelines for developing secure software?"
},
{
"id": "call_knzoxmifiotch0gejmlgb4",
"type": "function",
"function": {
"name": "retrieve_knowledge",
"arguments": {'query': 'best pra... | INCORRECT | PARAM_VALUE_ERROR | ['The correct query uses the preposition 'for', which accurately reflects 'practices intended for' secure software development. The incorrect query uses 'of', which subtly changes the meaning to 'practices belonging to' or 'practices within the scope of', potentially leading to different or less precise search results.... |
['{\'type\': \'function\', \'function\': {\'name\': \'get_fruit_nutrition\', \'description\': \'\\n Get nutritional information and details for a given fruit name.\\n\\n Args:\\n fruit_name: The name of the fruit to get information about (e.g., "apple", "banana", "orange")\\n\\n Returns:\\n Dicti... | [
{"role": "system", "content": "You are an intelligent assistant capable of interacting with various tools to provide information and perform actions. Here's a list of the tools you can use and how to use them:
1. `get_fruit_nutrition(fruit_name: str)`: Use this tool to retrieve nutritional information for a spe... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly requested 'patient_records.csv' and specified it as 'comma-separated'. The incorrect parameters use 'patinet_records.csv' (a spelling error, 'i' and 'e' swapped) and ';', a semicolon, as the delimiter, which does not match the 'comma-separated' instruction.'] |
['{\'type\': \'function\', \'function\': {\'name\': \'get-related-address\', \'description\': \'Retrieves all related identities associated with a specific platform identity. This tool helps discover cross-platform connections for the same person or entity. Use cases include: 1) Finding all accounts (Lens, Farcaster, E... | [
{
"role": "user",
"content": "I need to set up a connection to our main customer data warehouse. It's a PostgreSQL instance running on prod-db-01.example.com, port 5432. My login is analytics_user with password secureP@ss123, and the database is called customer_data."
},
{
"ty... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly stated 'port 5432' in their query, but the 'incorrect_tool_call_1_params' specifies 'port: 5433'. This is an off-by-one error.'] |
["{'name': 'write_dofile', 'description': 'write the stata-code to dofile', 'inputSchema': {'type': 'object', 'title': 'write_dofileArguments', 'required': ['content'], 'properties': {'content': {'type': 'string', 'title': 'Content'}}}}", "{'type': 'function', 'function': {'name': 'read_log', 'description': '\\n Rea... | [
{"role": "system", "content": "You are an AI assistant designed to help users interact with Stata and manage related tasks. You have access to the following tools:
* `write_dofile(filename: str, content: str)`: Creates a new Stata do-file with the specified content. Use this when the user asks to create a *new... | INCORRECT | PARAM_VALUE_ERROR | ['The 'filename' in the incorrect parameters is 'my_stata_analsis.do', which has a subtle typo (missing 'y' in 'analysis') compared to the correct 'my_stata_analysis.do'. Additionally, the 'content' has two subtle errors: 'regres' instead of 'regress' (missing 's') and 'mpe' instead of 'mpg' (a single letter difference... |
["{'type': 'function', 'function': {'name': 'get_thing', 'description': 'Get detailed information for the specified id(s) (up to 20) of board games.', 'parameters': {'properties': {'id': {'type': 'string', 'description': 'BGG ID(s) of the game(s), can be comma-separated, up to 20'}, 'type': {'type': 'string', 'descript... | [
{"role": "system", "content": "You are an AI assistant designed to help with creative and technical tasks. You have access to the following tools:
1. `search_ui_inspiration(query: str, category: Optional[str] = None, platform: Optional[str] = None, style: Optional[str] = None)`: Searches for UI design inspiration... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
["{'type': 'function', 'function': {'name': 'reasoning', 'description': 'Reasoning operations', 'parameters': {'properties': {}, 'required': []}}}", "{'name': 'visualization', 'annotations': {'_def': {'options': [{'_def': {'catchall': {'_def': {'typeName': 'ZodNever'}, '~standard': {'vendor': 'zod', 'version': 1}}, 'ty... | [
{"role": "system", "content": "You are a highly capable assistant with access to several specialized tools. Your primary goal is to accurately fulfill user requests by selecting the most appropriate tool and providing all necessary parameters.
Tools available:
- 'reasoning': Use this tool when a user's request ... | INCORRECT | PARAM_VALUE_ERROR | ['The user requested sales for the 'North' region, but the incorrect parameters contain a subtle typo, 'Norht', for the region filter. This one-letter difference would likely result in no data being displayed or an incorrect filtering of the data, as it doesn't match the intended region.'] |
["{'type': 'function', 'function': {'name': 'answer_question_with_rag', 'description': 'Answer the given question using documentation rag with knowledge base', 'parameters': {'properties': {'query': {'type': 'string', 'title': 'Query', 'description': 'search related data search from knowledge base'}}, 'required': ['que... | [
{
"role": "user",
"content": "Based on the knowledge base, can you explain the process for data backup?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
['{\'name\': \'cancel_leave_event\', \'description\': \'\\nCancel a leave request of a worker\\n\\nArgs:\\n event_id (str): The ID of the business process event to cancel. This is a uuid example ("43fa59c7367a100164bfb87ede060000")\\n You can get this ID by calling the get_worker_leave_process_ev... | [
{
"role": "user",
"content": "Can you find details for an active employee named John Doe?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_mrkcpsx27q94dmexd",
... | INCORRECT | PARAM_VALUE_ERROR | ['The user specifically asked for 'John Doe', but the 'name' parameter in the incorrect tool call is 'Jon Doe', which is a one-letter typo, creating a subtle mismatch with the user's intended query.'] |
["{'name': 'add', 'description': 'Add two numbers', 'inputSchema': {'type': 'object', 'title': 'addArguments', 'required': ['a', 'b'], 'properties': {'a': {'type': 'integer', 'title': 'A'}, 'b': {'type': 'integer', 'title': 'B'}}}}", "{'name': 'create_meeting', 'description': 'Create a new Zoom meeting', 'inputSchema':... | [
{"role": "system", "content": "You are a helpful assistant with access to a powerful tool for recommending places on Kakao Map. Use the `kakao_map_place_recommender` tool to find and recommend places based on user queries. This tool can locate various establishments like restaurants, cafes, attractions, or specif... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
['{\'name\': \'plausible_query\', \'description\': \'Query analytics data from Plausible\', \'inputSchema\': {\'type\': \'object\', \'required\': [\'site_id\', \'metrics\', \'date_range\'], \'properties\': {\'metrics\': {\'type\': \'array\', \'items\': {\'type\': \'string\'}, \'description\': \'$1f\'}, \'site_id\': {\'... | [
{"role": "system", "content": "You have access to a tool named 'plausible_query'. This tool is designed to retrieve various metrics and data points from a plausible analytics data source. You should use 'plausible_query' whenever a user asks for specific data, statistics, or reports that can be answered by queryi... | INCORRECT | PARAM_VALUE_ERROR | ['The 'end_date' in the incorrect parameters is '2023-10-30'. This is one day short, as October 2023 has 31 days, and the user explicitly asked for data for the entire month of October.'] |
['{\'name\': \'search_for_users\', \'description\': \'Search for users on Clado using filters like query, school, and match threshold.\', \'inputSchema\': {\'type\': \'object\', \'$schema\': \'http://json-schema.org/draft-07/schema#\', \'required\': [\'query\'], \'properties\': {\'limit\': {\'type\': \'number\', \'defa... | [
{"role": "system", "content": "You are an AI assistant designed to help users manage and retrieve professional data. You have access to the following tools:
1. `search_for_users(query: str, limit: int)`: Use this tool to search for users based on a general query, like names or job titles, across various platfor... | INCORRECT | PARAM_VALUE_ERROR | ['The 'company_name' parameter in the incorrect tool call is 'Tech Innovationss Inc.' which contains a subtle one-letter difference (an extra 's') compared to the user's request 'Tech Innovations Inc.'. This minor typo would lead to a failed or incorrect search result.'] |
["{'name': 'listFiles', 'description': 'List files in a directory in the sandbox', 'inputSchema': {'type': 'object', 'properties': {'path': {'type': 'string', 'description': 'Path to list (defaults to root)'}}}}", "{'type': 'function', 'function': {'name': 'uploadFile', 'description': 'Upload a file to the sandbox', 'p... | [
{
"role": "user",
"content": "I need to upload the Q3 2023 sales report. It's a CSV with 'Product,UnitsSold,Revenue' headers, followed by 'Laptop,150,180000', 'Mouse,400,10000', and 'Keyboard,200,16000'. Please save it as 'sales_report_q3_2023.csv' in the '/data/' directory."
},
{
... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly requested the file to be saved as 'sales_report_q3_2023.csv' (lowercase 'q'). The incorrect tool call uses 'sales_report_Q3_2023.csv' (uppercase 'Q'), which is a subtle case mismatch in the filename that does not align with the user's specified path.'] |
["{'name': 'get_horoscope', 'description': 'Get your horoscope', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['type', 'time'], 'properties': {'time': {'type': 'string', 'description': 'Time type: today, nextday, week, month'}, 'type': {'type': 'string', 'descripti... | [
{"role": "system", "content": "You are an intelligent assistant designed to manage and manipulate archive files. You have access to the following tools to perform various compression and decompression tasks:
- `unzip(archive_path: str, output_path: str = None)`: Use this tool to decompress a single ZIP archive. ... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
['{\'name\': \'Translator_Agent\', \'description\': "Translate the user\'s message to Spanish, French, and Italian", \'inputSchema\': {\'type\': \'object\', \'title\': \'Translator_AgentArguments\', \'required\': [\'query\'], \'properties\': {\'query\': {\'type\': \'string\', \'title\': \'Query\'}}}}'] | [
{
"role": "user",
"content": "Can you translate 'Good morning, how is the weather today?' from English into French for me?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assi... | INCORRECT | PARAM_VALUE_ERROR | ['The 'target_language' parameter is misspelled as 'Franch' instead of the correct 'French'. This is a subtle one-letter difference that makes the parameter invalid.'] |
["{'type': 'function', 'function': {'name': 'gumroad_create_offer_code', 'description': 'Creates a new offer code for a product', 'parameters': {'properties': {'name': {'type': 'string', 'description': 'The name/code of the offer (coupon code used at checkout)'}, 'universal': {'type': 'boolean', 'description': 'Whether... | [
{
"role": "user",
"content": "Please show me all the sales for product 'prod_abc456' that happened before January 1st, 2023, for the customer with the email 'test@example.com'."
},
{
"id": "call_yl4dua6rn5kc1",
"type": "function",
"function": {
"nam... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type', 'invalid format'] |
["{'type': 'function', 'function': {'name': 'getLiveTemperature', 'description': '\\n Get live temperature for a specific location.\\n\\n Args:\\n latitude: The latitude coordinate (e.g., 40.7128 for New York)\\n longitude: The longitude coordinate (e.g., -74.0060 for New York)\\n\\n Returns:\\n ... | [
{"role": "system", "content": "You are an AI assistant with access to several tools. Use them to help the user efficiently and accurately.
**Available tools:**
- `getLiveTemperature(location: str)`: Retrieves the current live temperature for a specified location. Use this when the user asks for real-time temper... | INCORRECT | PARAM_VALUE_ERROR | ['The 'path' parameter in the incorrect tool call has a subtle typo. 'feedback' is misspelled as 'feedbac', leading to an incorrect file path that would likely result in a 'file not found' error, despite the user's request clearly implying the correct spelling.'] |
["{'name': 'get_whoop_cycles', 'description': 'Get WHOOP physiological cycle data (daily summaries) with optional date range and limit', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'number', 'default': 5, 'maximum': 50, 'minimum': 1, 'descript... | [
{
"role": "user",
"content": "Could you please get my 7 most recent WHOOP physiological cycles starting from June 1st, 2024, to June 15th, 2024?"
},
{
"type": "function_call",
"id": "call_m0bk77z7",
"name": "get_whoop_cycles",
"arguments": {'limit': 'se... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
['{\'type\': \'function\', \'function\': {\'name\': \'get_current_weather\', \'description\': \'\\n Get current weather for a specified location. \\n Parameters:\\n location: ... | [
{
"role": "user",
"content": "Could you tell me the current weather in Berlin, please? And I prefer the temperature in Celsius."
},
{
"type": "function_call",
"id": "call_mk4uu3ooy5cqqedjcoudxfs5lm0",
"name": "get_current_weather",
"arguments": {'city':... | INCORRECT | PARAM_VALUE_ERROR | ['The 'city' parameter in the incorrect call is 'Berliin', which contains a subtle typo with an extra 'i' compared to the correct city 'Berlin' mentioned in the user's query.'] |
["{'type': 'function', 'function': {'name': 'greet', 'description': 'Greet a user by name.', 'parameters': {'properties': {'name': {'type': 'string', 'title': 'Name'}}, 'required': ['name']}}}"] | [
{
"role": "user",
"content": "Say hello to Alice."
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
"stop_reason": "tool_calls",
"tool_calls"... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
['{\'type\': \'function\', \'function\': {\'name\': \'browser_save_as_pdf\', \'description\': \'Save the current page as a PDF\\n\\n Args:\\n outputPath: The path to save the PDF to - required\\n filename: The name of the PDF file - optional, default is "page.pdf"\\n format: The format of the PD... | [
{"role": "system", "content": "You are a helpful assistant with access to the following tools:
- `add(num1: float, num2: float)`: Adds two numbers together. Use this when the user explicitly asks to sum or add two numerical values.
- `calculate-bmi(height_cm: float, weight_kg: float)`: Calculates the Body Mass In... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
["{'name': 'get_website_status', 'description': '\\n Check the status of a website.\\n\\n This function takes a root domain as input and checks whether the website is up or down\\n by making a request to isitdownrightnow.com\\n\\n Args:\\n root_domain (str): The root domain of the website to check.\\... | [
{
"role": "user",
"content": "Can you check if example.com is currently accessible and running?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
"stop_r... | INCORRECT | PARAM_VALUE_ERROR | ['The user asked for 'example.com', but the incorrect parameter has a one-letter typo, changing it to 'exmple.com' (missing an 'a').'] |
["{'type': 'function', 'function': {'name': 'search_semantic_scholar', 'description': '\\n Search for papers on Semantic Scholar using a query string.\\n\\n Args:\\n query: Search query string\\n num_results: Number of results to return (default: 10)\\n\\n Returns:\\n List of dictionaries ... | [
{"role": "system", "content": "You are an AI assistant designed to manage articles. You have access to the following tools:
- `move_article_to_trash(article_id: str, reason: str)`: Use this tool to move a specific article to the trash. It requires the unique ID of the article and a brief reason for trashing.
- `u... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'type': 'function', 'function': {'name': 'fetch_news_headlines_by_query', 'description': '', 'parameters': {'properties': {'query': {'type': 'string', 'title': 'Query', 'default': 'sports'}}, 'required': []}}}", "{'name': 'fetch_latest_news_headlines', 'description': '', 'inputSchema': {'type': 'object', 'title': 'f... | [
{"role": "system", "content": "You are an intelligent assistant with access to a suite of tools for interacting with Wikipedia articles. Use the available tools to effectively answer user queries by summarizing articles or sections, retrieving article sections, finding related topics, searching Wikipedia, getting... | INCORRECT | PARAM_VALUE_ERROR | ['invalid enum value'] |
['{\'name\': \'getGranolaTranscript\', \'description\': \'Get transcript from a Granola meeting document ID\', \'inputSchema\': {\'type\': \'object\', \'$schema\': \'http://json-schema.org/draft-07/schema#\', \'required\': [\'documentId\'], \'properties\': {\'documentId\': {\'type\': \'string\', \'description\': "The G... | [
{"role": "system", "content": "You have access to a tool named `getGranolaTranscript` which retrieves the transcript of a specific meeting. `getGranolaTranscript(meetingId: string, format: 'text' | 'srt')`: Retrieves the transcript for the specified `meetingId`. The `format` parameter determines the output type, ... | INCORRECT | PARAM_VALUE_ERROR | ['The user requested the transcript in 'plain text', which maps to the 'text' format. The incorrect parameters use 'test' instead of 'text' for the `format` parameter, a subtle one-letter typo.'] |
["{'type': 'function', 'function': {'name': 'get_crypto_price', 'description': '', 'parameters': {'properties': {'coin_id': {'type': 'string', 'title': 'Coin Id'}}, 'required': ['coin_id']}}}", "{'type': 'function', 'function': {'name': 'get_pubmed_count', 'description': '\\n Get the number of PubMed results for mul... | [
{
"role": "user",
"content": "Could you please tell me how many results I can find on PubMed for 'atrial fibrillation' and 'ventricular tachycardia'?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'type': 'function', 'function': {'name': 'get_paper_author', 'description': 'Get a paper author by ID in PapersWithCode', 'parameters': {'properties': {'author_id': {'type': 'string', 'title': 'Author Id'}}, 'required': ['author_id']}}}", "{'name': 'list_papers_by_author_id', 'description': 'List the papers for a gi... | [
{"role": "system", "content": "You are an AI assistant specialized in animation information. You have access to the following tools to help users:
1. `get_popular_animations()`: Use this tool to retrieve a list of animations that are currently popular. It requires no parameters.
2. `get_animation_details(animatio... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'name': 'create-directory', 'description': 'Create a new directory on the FTP server', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['remotePath'], 'properties': {'remotePath': {'type': 'string', 'description': 'Path of the directory to create'}}, 'additionalPro... | [
{
"role": "user",
"content": "I need to download the file 'latest_report.docx' from the '/documents' folder on the FTP server."
},
{
"type": "function_call",
"id": "call_d93uie",
"name": "download-file",
"arguments": {'remotePath': 12345}
}
] | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
['{\'type\': \'function\', \'function\': {\'name\': \'post_wallet_address\', \'description\': "Get member\'s coin deposit wallet address (Private)", \'parameters\': {\'properties\': {\'coinCode\': {\'type\': \'string\', \'default\': \'BTC\', \'description\': \'Cryptocurrency symbol (e.g. BTC, ETH)\'}}, \'required\': []... | [
{
"role": "user",
"content": "Can you give me the latest ticker information for Bitcoin?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
"stop_reason":... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'name': 'cut_text', 'description': 'Cut text into chunks of up to 300 words each, with Chinese language support', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['text'], 'properties': {'text': {'type': 'string', 'description': 'Text to cut into chunks'}, 'maxWord... | [
{"role": "system", "content": "You are an AI assistant with access to a set of tools to help users. Your goal is to accurately understand the user's intent and invoke the correct tool with appropriate parameters.
Available tools:
- `cut_text(original_text: str, start_index: int, end_index: int)`: Extracts a subs... | INCORRECT | PARAM_VALUE_ERROR | ['The `start_index` for the word 'quick' should be 4. An index of 3 refers to the space character immediately preceding 'quick'. Setting `start_index` to 3 would result in extracting ' quick' (including the leading space) instead of just 'quick'.'] |
["{'type': 'function', 'function': {'name': 'get_players', 'description': 'Get player information for a specific sport', 'parameters': {'properties': {'sport': {'enum': ['nfl', 'mlb', 'nba', 'nhl'], 'type': 'string', 'description': 'Sport to get players for'}, 'playerId': {'type': 'string', 'description': 'Filter by sp... | [
{"role": "system", "content": "You have access to the `get_forecast` tool to retrieve weather forecasts. `get_forecast(location: str, unit: str)`: Fetches the weather forecast for a specified location. The `location` parameter is a string representing the city or region (e.g., 'London', 'Paris', 'Tokyo'). The `un... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
['{\'name\': \'get_component_details\', \'description\': \'Get detailed information about a specific shadcn/ui component\', \'inputSchema\': {\'type\': \'object\', \'required\': [\'componentName\'], \'properties\': {\'componentName\': {\'type\': \'string\', \'description\': \'Name of the shadcn/ui component (e.g., "acc... | [
{"role": "system", "content": "You are a helpful assistant with access to several tools. Use these tools to answer user queries efficiently and accurately.
Available tools:
- `get_component_details(component_id: str)`: Retrieves detailed information about a specific component using its unique ID. Use this when t... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly asked for 'the top 5 recent feedback entries', but the 'limit' parameter was incorrectly set to 6 instead of 5, requesting one extra entry than specified.'] |
["{'name': 'get-news', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['start', 'end', 'symbols'], 'properties': {'end': {'type': 'string'}, 'start': {'type': 'string'}, 'symbols': {'type': 'array', 'items': {'type': 'string'}}}, 'additionalProperties': False}}", "{'... | [
{
"role": "user",
"content": "I need to take my product with ID 'prod_12345' off the market temporarily. Can you disable it?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "as... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
["{'type': 'function', 'function': {'name': 'read_terminal_output', 'description': 'Reads the output from the active iTerm terminal', 'parameters': {'properties': {'linesOfOutput': {'type': 'integer', 'description': 'The number of lines of output to read.'}}, 'required': ['linesOfOutput']}}}", "{'name': 'write_to_termi... | [
{
"role": "user",
"content": "Please execute the 'git status' command in my iTerm terminal."
},
{
"type": "function_call",
"id": "call_utvd8zdgfz81x3",
"name": "write_to_terminal",
"arguments": {'command': False}
}
] | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'name': 'find-columns', 'description': 'Query Macrostrat stratigraphic columns', 'inputSchema': {'type': 'object', 'required': ['lat', 'lng', 'responseType'], 'properties': {'lat': {'type': 'number', 'description': 'A valid latitude in decimal degrees'}, 'lng': {'type': 'number', 'description': 'A valid longitude in... | [
{
"role": "user",
"content": "Search for the top 5 most recent, short, high-definition videos about 'Python for beginners' in the US region, that have closed captions available."
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'type': 'function', 'function': {'name': 'search_onyx', 'description': 'Search the Onyx backend for relevant documents', 'parameters': {'properties': {'query': {'type': 'string', 'description': 'The topic to search for'}, 'maxResults': {'type': 'integer', 'maximum': 10, 'minimum': 1, 'description': 'Maximum number o... | [
{
"role": "user",
"content": "What are the most recent advancements in artificial intelligence, specifically looking for news updates?"
},
{
"id": "call_byq3rw52vp5wusgi8ch3zlvctdrh4e",
"type": "function",
"function": {
"name": "search_onyx",
... | INCORRECT | PARAM_VALUE_ERROR | ['The user query asks for 'advancements' (plural), implying multiple recent developments. The incorrect parameter uses 'advancement' (singular), which subtly changes the scope of the search to focus on a single advancement or the concept in general, rather than a collection of recent developments as intended by the use... |
["{'type': 'function', 'function': {'name': 'search_semantic_scholar', 'description': '\\n Search for papers on Semantic Scholar using a query string.\\n\\n Args:\\n query: Search query string\\n num_results: Number of results to return (default: 10)\\n\\n Returns:\\n List of dictionaries ... | [
{"role": "system", "content": "You are a helpful assistant with access to several tools. You should use these tools to fulfill user requests efficiently and accurately.
- `get_website_urls(query: str)`: Use this tool to find a list of relevant website URLs for a given search query. This is useful when you need t... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
['{\'name\': \'get-rounds\', \'description\': \'Get all rounds data from OnSecurity from client in a high level summary. When replying, only include the summary, not the raw data and be sure to present the data in a way that is easy to understand for the client. Rounds can be pentest rounds, scan rounds, or radar round... | [
{"role": "system", "content": "You are a helpful assistant capable of interacting with a security analysis system. You have access to the following tools:
1. `get-rounds(status: str = "all", start_date: str = None, end_date: str = None)`: Use this tool to retrieve a list of security assessment rounds. You can fil... | INCORRECT | PARAM_VALUE_ERROR | ['The user requested 'all unread alerts from October 2023', which implies data up to and including October 31st. The 'end_date' parameter is incorrectly set to '2023-10-30', which would subtly exclude notifications from the last day of October, thus not fully satisfying the user's request.'] |
["{'type': 'function', 'function': {'name': 'fetch_reddit_post_content', 'description': '\\n Fetch detailed content of a specific post\\n \\n Args:\\n post_id: Reddit post ID\\n comment_limit: Number of top level comments to fetch\\n comment_depth: Maximum depth of comment tree to traverse... | [
{"role": "system", "content": "You are an AI assistant designed to generate media. You have access to the following tools:
- "speak(text: str)": Generates an audio output of the provided text. Use this when the user only wants to hear speech.
- "create_lipsync_video_by_text(text: str, actor_id: str, voice_id: str... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'name': 'dnstwist_lookup', 'description': '', 'inputSchema': {'type': 'object', 'required': ['domain'], 'properties': {'domain': {'type': 'string', 'title': 'Domain'}}, 'additionalProperties': False}}", "{'name': 'dnsrecon_lookup', 'description': '', 'inputSchema': {'type': 'object', 'required': ['target'], 'propert... | [
{"role": "system", "content": "You are a cybersecurity assistant capable of leveraging a suite of specialized tools to gather information and perform reconnaissance. Carefully analyze user requests to determine the most appropriate tool(s) to use. When a user asks for specific information that one of your tools c... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly asked for 'mail exchange records', which is correctly represented by the 'MX' record type. The incorrect parameter uses 'MAIL', which is not a valid or standard DNS record type abbreviation for dig_lookup, leading to an incorrect tool call despite being conceptually close.'] |
["{'type': 'function', 'function': {'name': 'busca_cep', 'description': 'Busca o cep de um cliente', 'parameters': {'properties': {'cep': {'type': 'string', 'description': 'Número do CEP'}}, 'required': ['cep']}}}"] | [
{"role": "system", "content": "You are an AI assistant capable of retrieving address information. You have access to the following tools:
- `busca_cep(cep: str)`: This tool is used to find address details (street, neighborhood, city, state) given a Brazilian postal code (CEP). You should call `busca_cep` when the... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly requested the address for '01001-000'. The incorrect parameter '01001-001' has a single digit difference (the last digit is '1' instead of '0'). While '01001-001' might be a valid CEP for a different location, it does not match the exact CEP provided by the user, and therefore would retrieve an in... |
['{\'name\': \'update_component\', \'description\': \'Generates update commands for Starwind UI components\', \'inputSchema\': {\'type\': \'object\', \'required\': [\'component\'], \'properties\': {\'options\': {\'type\': \'array\', \'items\': {\'type\': \'string\'}, \'description\': "Additional options for updating (e... | [
{"role": "system", "content": "You are a helpful assistant with access to the following tools:
- get_forecast(location: str, unit: Optional[str] = 'celsius'): Retrieves the weather forecast for a specified location and unit (default is Celsius).
- get_alerts(location: str): Fetches any active weather alerts for a... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.