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': 'convert_pdf_file', 'description': '\\n Convert local PDF file to Markdown, supports single file or file list\\n \\n Args:\\n file_path: PDF file local path or path list, can be separated by spaces, commas, or newlines\\n enable_ocr: Whether to enable O... | [
{
"role": "user",
"content": "Can you show me all the ERC20 tokens held by the address 0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045 on the Ethereum mainnet?"
},
{
"type": "function_call",
"id": "call_pj0jqwdcnty3jwwenx4jnmsn",
"name": "get_tokens_by_address",
... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'name': 'search_photos', 'description': '\\n Search for Unsplash photos\\n \\n Args:\\n query: Search keyword\\n page: Page number (1-based)\\n per_page: Results per page (1-30)\\n order_by: Sort method (relevant or latest)\\n color: Color filter (black_and_white, black, w... | [
{
"role": "user",
"content": "What's the current time and timezone information for New York City?"
},
{
"id": "call_04ombsglpawscbwn1j3",
"type": "function",
"function": {
"name": "getTimezoneInfo",
"arguments": {'location': 'New York Ct... | INCORRECT | PARAM_VALUE_ERROR | ['The 'location' parameter in the incorrect tool call has a subtle typo, 'Cty' instead of 'City', which does not accurately represent the user's intended location of 'New York City'.'] |
["{'name': 'search_photos', 'description': '\\n Search for Unsplash photos\\n \\n Args:\\n query: Search keyword\\n page: Page number (1-based)\\n per_page: Results per page (1-30)\\n order_by: Sort method (relevant or latest)\\n color: Color filter (black_and_white, black, w... | [
{"role": "system", "content": "You are a helpful assistant with access to several tools to assist users.
- `search_photos(query: str)`: Use this to find images based on a user's descriptive query. For example, 'search_photos(query="cats playing")'.
- `scrape_url_markdown(url: str)`: Use this to retrieve the cont... | INCORRECT | PARAM_VALUE_ERROR | ['The user query explicitly mentions 'London', but the `location` parameter in the incorrect tool call is 'Londn', which is a misspelling (missing 'o') and does not accurately reflect the requested city.'] |
["{'name': 'get_alerts', 'description': 'Get weather alerts for a US state.\\n\\nArgs:\\n state: Two-letter US state code (e.g. CA, NY)\\n', 'inputSchema': {'type': 'object', 'title': 'get_alertsArguments', 'required': ['state'], 'properties': {'state': {'type': 'string', 'title': 'State'}}}}", "{'name': 'get_weathe... | [
{"role": "system", "content": "You are a helpful assistant with access to several tools. Use the tools appropriately to answer user queries.
- `get_alerts(area: str)`: Use this tool to retrieve current safety alerts, advisories, or warnings for a specified geographical area. Call this when the user asks about ha... | INCORRECT | PARAM_VALUE_ERROR | ['The 'area' parameter in the incorrect call contains a subtle typo, 'Floarida' instead of 'Florida'. This single-letter difference makes the parameter invalid as it does not match the user's intended query for 'Florida'.'] |
['{\'name\': \'speak\', \'description\': "Speak text aloud using Rime\'s text-to-speech API. Should be used when user asks you to speak or to announce and explain when you finish a command\\n \\nUser configuration:\\n\\nWHO_TO_ADDRESS: Developer\\n\\nWHEN_TO_SPEAK: when finishing a command\\n\\nVOICE: cove\\n\\nGUID... | [
{
"role": "user",
"content": "Could you please say 'this is a test of the text-to-speech system' out loud for me?"
},
{
"id": "call_3spbf4ycja",
"type": "function",
"function": {
"name": "speak",
"arguments": {'text': 12345, 'reduceLaten... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
['{\'name\': \'smart_search\', \'description\': \'Perform intelligent search across multiple content types using cached metadata. This tool automatically searches all text fields in your content types for the given query term. Much faster and easier than manually chaining multiple GraphQL calls.\', \'inputSchema\': {\'... | [
{"role": "system", "content": "The assistant has access to a suite of tools for data interaction and retrieval. You should use these tools to answer user queries effectively and efficiently.
* `smart_search(query: str, type: Optional[str] = null, filters: Optional[dict] = null)`: Use this for general-purpose s... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly requested articles from 'the year 2023'. The incorrect parameters specify the year '2022' in the filters, which is a one-digit difference from the requested year, making the search results irrelevant to the user's specified time frame.'] |
['{\'name\': \'get_rss\', \'description\': \'\\n Fetch RSS feeds\\n Args:\\n feed_name: Feed name (e.g. "Example")\\n since: Get feeds after this date (e.g. "2025-04-13")\\n export_result: Whether to export the result to a text file\\n Returns:\\n Fetched text\\n \', \'inputSchem... | [
{
"role": "user",
"content": "Can you please check the availability for 'webcreations.net'?"
},
{
"type": "function_call",
"id": "call_fgovi103tx7iueq4vv97uiwvawgaz9",
"name": "check_domain_availability",
"arguments": {'domain_name': 'webcreations', 'tl... | INCORRECT | PARAM_VALUE_ERROR | ['The TLD in the incorrect parameters is 'com', which is different from the user's explicit request for '.net' for the domain 'webcreations'.'] |
["{'name': 'fish_audio_tts', 'description': 'Generate speech from text using Fish Audio TTS API', 'inputSchema': {'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string', 'maxLength': 10000, 'description': 'Text to convert to speech'}, 'format': {'enum': ['mp3', 'wav', 'pcm', 'opus'], 'type': '... | [
{
"role": "user",
"content": "Could you please generate audio for 'The quick brown fox jumps over the lazy dog' using a standard female voice at normal speed?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type... | INCORRECT | PARAM_VALUE_ERROR | ['The 'text' parameter in the incorrect call is 'The quick brown fox jump over the lazy dog.', which subtly differs from the user's requested text 'The quick brown fox jumps over the lazy dog.' by one letter (missing the 's' in 'jumps'). This makes the sentence grammatically incorrect and does not match the original qu... |
["{'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 assistant with access to several tools. Your goal is to respond to user queries by calling the appropriate tools with the correct parameters.
- `get_thing(item_id: str)`: Use this tool to retrieve detailed information about a specific item when its unique ID is known. Th... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly asked for the 'top 5' trending board games, but the 'limit' parameter in the incorrect tool call is set to 6, which requests one more item than the user specified.'] |
["{'type': 'function', 'function': {'name': 'get_word_details', 'description': '\\n Get detailed word information including pronunciation, synonyms, and examples.\\n \\n Args:\\n word: The word to get detailed information for\\n \\n Returns:\\n Detailed word information or error message\\n ... | [
{
"role": "user",
"content": "Could you please run the integration test suite, specifically version 3, against our staging environment?"
},
{
"id": "call_zhsgwilli0o3",
"type": "function",
"function": {
"name": "run-collection",
"argumen... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly asked for 'version 3' of the integration test suite, but the incorrect parameter specifies 'integration-suite-v2'. This is a one-number difference, making the collection ID subtly mismatched with the user's request.'] |
["{'type': 'function', 'function': {'name': 'get_comic_by_id', 'description': 'Fetch a single Marvel comic by ID', 'parameters': {'properties': {'comicId': {'type': 'number'}}, 'required': ['comicId']}}}", "{'name': 'generate_comics_html', 'description': 'Create an HTML page displaying Marvel comics with their images',... | [
{"role": "system", "content": "You are an assistant designed to interact with a comic book database. You have access to the following tools:
1. `get_comic_by_id(comic_id: str)`: Use this tool to fetch detailed information about a specific comic book when provided with its unique ID.
2. `generate_comics_html(co... | INCORRECT | PARAM_VALUE_ERROR | ['The incorrect parameter 'CH-O42' contains the uppercase letter 'O' where the correct ID 'CH-042' has the numeral '0'. This is a subtle but critical typographical error.'] |
["{'name': 'embeddings', 'description': 'Generate embeddings for a given text, pdf or image', 'inputSchema': {'type': 'object', 'required': ['text', 'type', 'token_overflow_mode'], 'properties': {'text': {'type': 'string', 'description': 'The text to generate embeddings for'}, 'type': {'enum': ['text', 'image', 'audio'... | [
{
"role": "user",
"content": "Please generate embeddings for the following text: 'The quick brown fox jumps over the lazy dog'. If the text exceeds the token limit, please truncate it. The content type is text."
},
{
"role": "assistant",
"stop_reason": "tool_use",
... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'type': 'function', 'function': {'name': 'write_note', 'description': 'Write note to flomo', 'parameters': {'properties': {'content': {'type': 'string', 'description': 'Text content of the note with markdown format'}}, 'required': ['content']}}}"] | [
{
"role": "user",
"content": "Could you please make a note for me? The title should be 'Project Update' and the content needs to be 'Final review of the 'Alpha' project is scheduled for next Monday at 10 AM. All team leads must be present.'"
},
{
"completion_message": {
... | INCORRECT | PARAM_VALUE_ERROR | ['The user's query explicitly refers to the 'Alpha' project, but the incorrect tool call subtly changes it to the 'Beta' project in the content, which is a one-word difference and a factual mismatch.'] |
["{'name': 'listProcedures', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'max_items': {'type': 'integer', 'description': 'Optional maximum number of procedures to include in the formatted text output.', 'exclusiveMinimum': 0}, 'max_length': {'type': 'integer', ... | [
{
"role": "user",
"content": "I need to find procedures for troubleshooting engine issues."
},
{
"type": "function_call",
"id": "call_9z6k9f51i0idmwkqe68t86sbzwaa",
"name": "searchProcedures",
"arguments": {'query': 'engine diagnoistics'}
}
] | INCORRECT | PARAM_VALUE_ERROR | ['The 'query' parameter has a subtle one-letter typo ('diagnoistics' instead of 'diagnostics'), which would likely result in incorrect or no search results, failing to accurately reflect the user's request for 'troubleshooting engine issues'.'] |
["{'type': 'function', 'function': {'name': 'getSecondOpinion', 'description': 'Get responses from various LLM providers', 'parameters': {'properties': {'model': {'type': 'string', 'minLength': 1}, 'top_k': {'type': 'number', 'exclusiveMinimum': 0}, 'top_p': {'type': 'number', 'maximum': 1, 'minimum': 0}, 'prompt': {'t... | [
{
"role": "user",
"content": "My patient, ID PAT-789012, is still suffering from persistent, undiagnosed chronic fatigue. I'd like to get a second opinion on their case."
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
... | INCORRECT | PARAM_VALUE_ERROR | ['The `patientId` 'PAT-789013' in the incorrect parameters differs by one digit from the 'PAT-789012' specified in the user's request. This subtle off-by-one error would lead to requesting a second opinion for the wrong patient.'] |
["{'name': 'get_poi_names', 'description': '\\n Gets a simplified list of POI names near specified coordinates.\\n\\n Args:\\n coordinates: A (longitude, latitude) tuple for the center point.\\n buffer: Search radius in meters (default: 1000m).\\n limit: Maximum number of POIs to return (defa... | [
{"role": "system", "content": "You are a helpful assistant with access to a suite of geospatial tools. Carefully consider the user's request and select the most appropriate tool(s) and parameters.
Tools available:
- `geocode_address(address: str)`: Converts a human-readable address into geographic coordinates (... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly asked for the reachable area within '30 minutes', but the 'travel_time' parameter in the incorrect tool call is set to '20'. This is a subtle numerical mismatch of a single parameter value compared to the user's request.'] |
['{\'name\': \'convert_video\', \'description\': \'\\n Converts a video file to the specified output format using FFmpeg.\\n\\n Args:\\n input_file_path: The absolute path to the input video file.\\n output_format: The desired output format (e.g., "mp4", "webm", "mov").\\n quality: Optional q... | [
{
"role": "user",
"content": "Hey, I've got this video 'my_holiday_trip.mov' located at https://example.com/videos/my_holiday_trip.mov. Could you convert it to MP4, make sure it's 720p, and keep the bitrate around 3 Mbps?"
},
{
"role": "assistant",
"stop_reason": "tool... | INCORRECT | PARAM_VALUE_ERROR | ['The user requested '720p' resolution, which correctly translates to '1280x720'. The 'resolution' parameter in the incorrect call, '1280x72p', contains a subtle typo ('p' instead of '0') making it an invalid or non-standard resolution format, thus not aligning with the user's explicit request.'] |
["{'type': 'function', 'function': {'name': 'list_splunk_alerts', 'description': 'List all Splunk alerts (saved searches with actions). Supports pagination and optional case-insensitive title filter.', 'parameters': {'properties': {'count': {'type': 'number', 'description': 'Number of results to return (default 10)'}, ... | [
{
"role": "user",
"content": "Show me the first 5 Splunk alerts that have 'Login Failure' in their title, starting from the beginning."
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'name': 'get-market-orders', 'description': 'Get market orders from a specific region', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['region_id'], 'properties': {'type_id': {'type': 'number', 'description': 'Item type ID to filter orders'}, 'region_id': {'type'... | [
{"role": "system", "content": "You are an AI assistant designed to help with design-related tasks by interacting with Figma. You have access to the following tool:
- `get_figma_data(file_id: str, data_type: str)`: This tool retrieves specific design data from a Figma file.
- `file_id`: The unique identifier for... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
['{\'name\': \'get_build_failure_logs\', \'description\': \'\\n This tool helps debug CircleCI build failures by retrieving failure logs.\\n\\n Input options (EXACTLY ONE of these two options must be used):\\n\\n Option 1 - Direct URL (provide ONE of these):\\n - failedJobURL: The URL of the failed CircleCI... | [
{"role": "system", "content": "The assistant can use the following tools:
- order_food(item_name: str, quantity: int, special_instructions: str = None): Orders food from a restaurant. Use this tool when the user explicitly wants to place an order for a specific food item.
- find_menu_options(cuisine: str = null, ... | INCORRECT | PARAM_VALUE_ERROR | ['invalid data type'] |
["{'name': 'get_latest_result', 'description': 'Get the latest results for a specific query ID as a CSV string on dune analytics', 'inputSchema': {'type': 'object', 'title': 'get_latest_resultArguments', 'required': ['query_id'], 'properties': {'query_id': {'type': 'integer', 'title': 'Query Id'}}}}"] | [
{
"role": "user",
"content": "Can you fetch me the most recent result for the test with ID 'TC_API_AUTH_001'?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
... | INCORRECT | PARAM_VALUE_ERROR | ['The 'test_id' in the incorrect parameters is 'TC_API_AUTH_01', which is missing a '0' compared to the user's requested 'TC_API_AUTH_001'. This is a subtle one-character difference (a missing digit).'] |
["{'name': 'check_space_availability', 'description': 'Check if a Twitter Space is available for download', 'inputSchema': {'type': 'object', 'required': ['space_url'], 'properties': {'space_url': {'type': 'string', 'description': 'Full Twitter Space URL (e.g., https://x.com/i/spaces/1ZkKzYLnWOLxv)'}}}}", "{'type': 'fu... | [
{
"role": "user",
"content": "Could you please download the audio and get a transcript for the Twitter Space with the ID 1zqJVXqXkZqGB?"
},
{
"id": "call_osi1xhu2828yni89lc311",
"type": "function",
"function": {
"name": "download_and_transcribe_spac... | INCORRECT | PARAM_VALUE_ERROR | ['The 'space_id' in the incorrect parameters ('1zqJVXqXkZqG8') subtly differs from the correct ID ('1zqJVXqXkZqGB') by one character ('8' instead of 'B' at the end). This minor discrepancy would prevent the tool from locating the correct Twitter Space for download and transcription.'] |
["{'type': 'function', 'function': {'name': 'get_character_info', 'description': '\\n get information about a Disney character by name.\\n ', 'parameters': {'properties': {'medicine_name': {'type': 'string', 'title': 'Medicine Name'}}, 'required': ['medicine_name']}}}", '{\'name\': \'save_text\', \'description\':... | [
{
"role": "user",
"content": "Could you please save my shopping list to a file called `groceries.txt`? The list is: milk, bread, eggs, and cheese."
},
{
"type": "function_call",
"id": "call_ljzai02u691iqoghu6hwlcla",
"name": "save_text",
"arguments": {'... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
['{\'name\': \'get-deepseek-thinker\', \'description\': \'think with deepseek\', \'inputSchema\': {\'type\': \'object\', \'required\': [\'originPrompt\'], \'properties\': {\'originPrompt\': {\'type\': \'string\', \'description\': "user\'s original prompt"}}}}'] | [
{
"role": "user",
"content": "I need to write a short story for my class. Can you help me brainstorm some ideas for a story about a time-traveling librarian?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type"... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
['{\'type\': \'function\', \'function\': {\'name\': \'get_sitemap_pages\', \'description\': "Get all pages from a website\'s sitemap with optional limits and filtering options. Supports cursor-based pagination.", \'parameters\': {\'properties\': {\'url\': {\'type\': \'string\', \'title\': \'Url\', \'description\': \'Th... | [
{
"role": "user",
"content": "Could you please give me a list of all the pages included in the sitemap at https://www.example.com/sitemap.xml?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly provided 'sitemap.xml' with a lowercase 'xml' extension. The incorrect parameter uses 'sitemap.XmL', which has a capitalized 'XmL', creating a subtle mismatch in the file extension that could lead to a 'Not Found' error if the server is case-sensitive.'] |
["{'name': 'execute_query', 'description': '\\n Executes a query on the database.\\n Make sure that you lower case the text and the column compared and use the LIKE operator. This is very important.\\n ', 'inputSchema': {'type': 'object', 'title': 'execute_queryArguments', 'required': ['query'], 'properties': ... | [
{
"role": "user",
"content": "Can you list the top 5 newest customers from the 'North' region who registered this year? I just need their basic contact info."
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type"... | INCORRECT | PARAM_VALUE_ERROR | ['The 'region' condition in the incorrect query uses 'Norh' instead of 'North', which is a one-letter typo that would cause the query to return no results or incorrect results.'] |
['{\'type\': \'function\', \'function\': {\'name\': \'open_task_details\', \'description\': "Get details of a specific task by \'taskId\'. This is for inspecting task information at any point.", \'parameters\': {\'properties\': {\'taskId\': {\'type\': \'string\'}}, \'required\': [\'taskId\']}}}', '{\'name\': \'update_t... | [
{"role": "system", "content": "You are an AI assistant tasked with finding restaurants. When a user expresses a desire to search for dining options, use the `get_restaurants` tool. This tool can find restaurants based on various criteria. You must provide a `cuisine` type and a `location`. Optionally, you can als... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
["{'name': 'image_adjust_saturation', 'description': 'Adjust image saturation', 'inputSchema': {'type': 'object', 'required': ['input_path', 'output_path', 'saturation'], 'properties': {'input_path': {'type': 'string', 'description': 'Path to input image'}, 'saturation': {'type': 'number', 'maximum': 2, 'minimum': 0, '... | [
{
"role": "user",
"content": "Please create a solid blue image with a width of 1920 pixels and a height of 1080 pixels, and save it to 'assets/new/solid_blue.png'."
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
["{'type': 'function', 'function': {'name': 'execute_query', 'description': 'Execute a SQL query on Snowflake', 'parameters': {'properties': {'query': {'type': 'string', 'description': 'SQL query to execute'}}, 'required': ['query']}}}"] | [
{
"role": "user",
"content": "Can you pull up the sales figures for products in the North region for January?"
},
{
"type": "function_call",
"id": "call_me4zpyutfgdkfl4fbz2950ust8ev4",
"name": "execute_query",
"arguments": {'query_string': "SELECT produ... | INCORRECT | PARAM_VALUE_ERROR | ['The 'query_string' contains a subtle typo; 'Januari' should be 'January'. This single letter difference makes the month condition incorrect and would likely result in no data or an error depending on the database's strictness.'] |
["{'type': 'function', 'function': {'name': 'send_note', 'description': '\\n Send a note to the Inbox API.\\n\\n Args:\\n content: Content of the note (max 3000 characters)\\n title: Optional title of the note\\n\\n Returns:\\n A dictionary containing the API response\\n ', 'parameters'... | [
{
"role": "user",
"content": "Could you send a note to Alice Smith? Tell her to please review the Q3 budget report by end of day Friday."
},
{
"type": "function_call",
"id": "call_lnhfdc58bb2orgzf8hokkb7tdaslr",
"name": "send_note",
"arguments": {'recip... | INCORRECT | PARAM_VALUE_ERROR | ['The 'recipient' parameter in the incorrect tool call, 'Alyce Smith', has a single letter difference ('y' instead of 'i') compared to the user's requested recipient, 'Alice Smith'.'] |
["{'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 kick off a new build for the 'auth-service' project from the 'develop' branch and deploy it to our staging environment?"
},
{
"id": "call_61dq70ojv4",
"type": "function",
"function": {
"name": "trigger_... | INCORRECT | PARAM_VALUE_ERROR | ['The 'branch_name' in the incorrect parameters is 'devlop', which is a one-letter typo ('e' is missing) compared to the 'develop' branch requested in the user's query.'] |
['{\'type\': \'function\', \'function\': {\'name\': \'homeassistant_get_state\', \'description\': \'Get the current state of a Home Assistant entity\', \'parameters\': {\'properties\': {\'entity_id\': {\'type\': \'string\', \'description\': "The entity ID (e.g., \'light.living_room\', \'sensor.temperature\')"}}, \'requ... | [
{"role": "system", "content": "You are a helpful AI assistant that can interact with Home Assistant. You have access to the following tools:
1. `homeassistant_list_entities()`: Use this tool to retrieve a list of all available entities, optionally filtered by `domain` (e.g., 'light', 'sensor') or `integration` (... | INCORRECT | PARAM_VALUE_ERROR | ['The user query asks for 'lighting devices', but the `homeassistant_list_entities` tool's 'domain' parameter expects the specific Home Assistant domain 'light' for lighting devices, not 'lighting'. 'lighting' is not a valid or recognized domain within Home Assistant for this purpose.'] |
["{'name': 'get-alerts', 'description': 'Get weather alerts for a state', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['state'], 'properties': {'state': {'type': 'string', 'maxLength': 2, 'minLength': 2, 'description': 'Two-letter state code (e.g., CA, NY'}}, 'add... | [
{
"role": "user",
"content": "Show me all the database servers that are available in the JDBCX server."
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_bkofl7gk5l5kx... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
["{'name': 'analyse_poker_cards', 'description': '$20', 'inputSchema': {'type': 'object', 'title': 'analyse_poker_cardsArguments', 'required': ['my_cards_input', 'community_input', 'opponent_input'], 'properties': {'my_cards_input': {'type': 'string', 'title': 'My Cards Input'}, 'opponent_input': {'type': 'string', 'ti... | [
{
"role": "user",
"content": "What's the current crowding level like at London Bridge Station?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_ujiyzn8",
... | INCORRECT | PARAM_VALUE_ERROR | ['The user query specifies 'London Bridge Station', but the 'station_name' parameter in the incorrect tool call is 'London Bridg Station', which is a subtle misspelling (missing the 'e' from 'Bridge').'] |
['{\'name\': \'search_entity\', \'description\': \'\\n Search for a Wikidata entity ID by its query.\\n\\n Args:\\n query (str): The query to search for. The query should be unambiguous enough to uniquely identify the entity.\\n\\n Returns:\\n str: The Wikidata entity ID corresponding to the give... | [
{
"role": "user",
"content": "Can you find information about the Eiffel Tower for me?"
},
{
"id": "call_fxogweg",
"type": "function",
"function": {
"name": "search_entity",
"arguments": {'query': 'Eifel Tower', 'language': 'en'}
... | INCORRECT | PARAM_VALUE_ERROR | ['The 'query' parameter in the incorrect tool call has a subtle one-letter typo: 'Eifel Tower' instead of 'Eiffel Tower'. This small difference means the tool would likely fail to find the correct entity or return irrelevant results, despite the user clearly asking for 'Eiffel Tower'.'] |
["{'name': 'plan', 'description': '\\n A tool for managing a development work plan for a ticket, organized by PRs and commits.\\n Register or update the whole work plan for the current ticket you assigned to.\\n\\n Before using this tool, you **MUST**:\\n - Understand requirements, goals, and specifications... | [
{
"role": "user",
"content": "Update the SEO title for page '60c7a8b3e8b3a40011e47b31' to 'New SEO Title for Our Services Page' and the SEO description to 'Explore our wide range of professional services designed to help your business grow.'"
},
{
"id": "call_1jy0a2nb6nv755u2a... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'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": "user",
"content": "What's the phone number for the fire department?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_pgu4zwu6snaum35qc6hzfawv2r1v0i",
... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly asked for the 'fire department', referring to the emergency service. The incorrect parameter 'firestation' subtly differs, potentially referring to the physical building rather than the specific emergency contact service that the tool is designed to provide.'] |
["{'type': 'function', 'function': {'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.', ... | [
{
"role": "user",
"content": "Could you please retrieve the Trello card from this link: https://trello.com/c/aBcDeFgH/42-design-new-logo?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'name': 'add', 'description': 'Add two numbers', 'inputSchema': {'type': 'object', 'required': ['a', 'b'], 'properties': {'a': {'type': 'integer', 'title': 'A'}, 'b': {'type': 'integer', 'title': 'B'}}}, 'outputSchema': {'type': 'object', 'title': '_WrappedResult', 'required': ['result'], 'properties': {'result': {'... | [
{"role": "system", "content": "You have access to the following tool:
`add(num1: float, num2: float)`: This tool adds two numbers together and returns their sum. You should use this tool whenever the user explicitly requests to calculate the sum of two or more numerical values. Ensure you extract the exact numeri... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly asked to add 'seven point two', but the incorrect parameters provided '7.3' as the second number, which is an off-by-one difference from the intended value.'] |
['{\'name\': \'get_news_by_country\', \'description\': \'Get latest news from a specific country\', \'inputSchema\': {\'type\': \'object\', \'required\': [\'country\'], \'properties\': {\'country\': {\'type\': \'string\', \'description\': "Country code (e.g., \'us\', \'tr\', \'gb\')"}, \'category\': {\'enum\': [\'busin... | [
{
"role": "user",
"content": "Find me news articles about the impact of cryptocurrency on the global economy, written in English."
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'name': 'search_contacts', 'description': '\\n Search for HubSpot contacts based on property criteria\\n\\n Args:\\n property_name: The contact property to search (e.g., firstname, lastname, email)\\n operator: The operator to use for searching (EQ, CONTAINS, NEQ, GT, LT, GTE, LTE)\\n valu... | [
{"role": "system", "content": "You are an AI assistant capable of interacting with various tools to assist the user. Your capabilities include managing Spotify, searching for information, handling Airbnb listings, and internal data operations. Carefully analyze the user's request and determine which tool, if any,... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'name': 'cancel_request', 'description': 'Cancel a request by setting its status to cancelled\\n\\nArgs:\\n request_id: Unique identifier of the request to cancel\\n', 'inputSchema': {'type': 'object', 'title': 'cancel_requestArguments', 'required': ['request_id'], 'properties': {'request_id': {'type': 'string', ... | [
{
"role": "user",
"content": "Could you please permanently delete the request identified as REQ-789012 from our records? I no longer need it."
},
{
"id": "call_7xj75pn1hsudj56zx1p01ozxjff9",
"type": "function",
"function": {
"name": "delete_request"... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly mentioned 'REQ-789012' in their query, but the incorrect parameter provided 'REQ-789011'. This is a one-number difference, making it a plausible but incorrect ID for the intended operation.'] |
['{\'type\': \'function\', \'function\': {\'name\': \'flow_getBalance\', \'description\': \'Retrieves the balance of a given Flow EVM address\', \'parameters\': {\'properties\': {\'address\': {\'type\': \'string\', \'pattern\': \'^0x[a-fA-F0-9]{40}$\', \'description\': \'The Flow EVM address to check balance\'}, \'bloc... | [
{
"role": "user",
"content": "I need to execute a read-only call to the contract at '0xf02c1c8e6114b1dbe8937a39260b5b5a4874487b' to check a value. The call data is '0xc6888fa10000000000000000000000000000000000000000000000000000000000000003'. Please simulate this call from address '0xf02c1c8e6... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'type': 'function', 'function': {'name': 'read_log', 'description': '\\n Read the log file and return its content.\\n\\n Args:\\n log_path (str): The path to the log file.\\n\\n Returns:\\n str: The content of the log file.\\n ', 'parameters': {'properties': {'log_path': {'type': 'string', ... | [
{
"role": "user",
"content": "Can you run a regression for me? I want to see how 'sales' are affected by 'advertising' and 'promotions' using the 'marketing_campaign.dta' dataset. Please make sure to clear any existing data first."
},
{
"completion_message": {
"con... | INCORRECT | PARAM_VALUE_ERROR | ['The incorrect parameters contain a subtle typo in one of the regression variables. The user requested 'advertising', but the `code` parameter includes 'advertizing', which is a one-letter difference and would cause Stata to report an 'unrecognized variable' error.'] |
["{'name': 'generate_flux_image', 'description': '\\n Generate an image using Flux stable diffusion model.\\n \\n Args:\\n prompt: The image description to generate\\n output_dir: Directory to save the image (defaults to current directory)\\n cfg_scale: CFG scale parameter (default: 1.0)\\... | [
{
"role": "user",
"content": "Can you generate a cyberpunk image of a futuristic city at sunset, with neon reflections on wet streets? I'd like it widescreen, perhaps 16:9, and a decent resolution."
},
{
"type": "function_call",
"id": "call_w7w0gveifln67qrrb",
... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly requested a 'widescreen' image and suggested an '16:9' aspect ratio. While the 'aspect_ratio' parameter correctly reflects '16:9', the 'resolution' parameter of '1024x768' corresponds to a 4:3 aspect ratio, directly contradicting the user's explicit desire for a widescreen output. This is a subtle... |
["{'name': 'plan', 'description': '\\n A tool for managing a development work plan for a ticket, organized by PRs and commits.\\n Register or update the whole work plan for the current ticket you assigned to.\\n\\n Before using this tool, you **MUST**:\\n - Understand requirements, goals, and specifications... | [
{"role": "system", "content": "You are an assistant capable of managing project plans. You have access to the following tools:
1. `plan(project_name: str, start_date: str, end_date: str, tasks: list[str])`: Use this tool to create a new project plan. It requires the `project_name`, a `start_date` (format YYYY-MM... | INCORRECT | PARAM_VALUE_ERROR | ['The 'project_name' parameter in the incorrect tool call is 'Websiet Redesign', which contains a subtle typo ('siet' instead of 'site'). The user query explicitly states 'Website Redesign', making the 'Websiet' value an incorrect match.'] |
["{'name': 'add_bookmark', 'description': 'Add a new bookmark to Raindrop.io\\n \\n Args:\\n url: The URL to bookmark (required)\\n title: Title for the bookmark (optional, will be extracted from URL if not provided)\\n description: Description/excerpt for the bookmark (optional)\\n ta... | [
{
"role": "user",
"content": "Please bookmark the article at 'https://www.theverge.com/22718447/how-to-build-a-pc-2021-guide' with the title 'How to build a PC in 2021'. Add a description 'A detailed guide on building a personal computer in 2021.' and tag it with 'tech', 'diy', and 'pc_buildi... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'type': 'function', 'function': {'name': 'set_download_directory', 'description': 'Set the main local download folder for markdown files', 'parameters': {'properties': {'directory': {'type': 'string', 'description': 'Full path to the download directory'}}, 'required': ['directory']}}}", "{'name': 'create_subdirector... | [
{"role": "system", "content": "You are an AI assistant designed to manage file downloads and organization. You have access to the following tools:
- `set_download_directory(path: str)`: Sets the primary directory where all future files will be downloaded. Use this when the user specifies a new main download locat... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly asked for a folder named 'daily summaries'. While the incorrect parameter uses a hyphen ('-'), the correct parameter 'daily_summaries' uses an underscore ('_'), which is a common convention for replacing spaces in directory names for better system compatibility. The incorrect parameter has a one-c... |
["{'type': 'function', 'function': {'name': 'search_crypto', 'description': '\\n Search for coins, categories and markets.\\n\\n Args:\\n query: Search query string\\n ', 'parameters': {'properties': {'query': {'type': 'string', 'title': 'Query'}}, 'required': ['query']}}}", '{\'type\': \'function\', \'... | [
{"role": "system", "content": "You are a helpful assistant with access to cryptocurrency data tools. Use these tools to answer user queries accurately and efficiently.
Tools available:
- `search_crypto(query: str)`: Use this tool to find cryptocurrencies by their name or partial name. It's useful when a user is... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly asked for 'Ethereum'. The incorrect parameter 'Ethereumm' contains a subtle typo, adding an extra 'm' at the end, which does not match the user's requested cryptocurrency name.'] |
["{'name': 'get_substance_details', 'description': '\\n Get detailed information about a specific substance by its PubChem SID.\\n \\n Args:\\n sid: PubChem Substance ID (SID)\\n \\n Returns:\\n Dictionary with substance details\\n ', 'inputSchema': {'type': 'object', 'title': 'get_s... | [
{
"role": "user",
"content": "I need to find all bioassays related to BRAF inhibitors. Can you pull the top 3?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_5u0rh... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'type': 'function', 'function': {'name': 'execute_custom_query', 'description': 'Execute a custom SQL query against the database. WARNING: Use with care. Do not expose to untrusted input.', 'parameters': {'properties': {'query': {'type': 'string', 'description': 'SQL query to execute'}, 'values': {'type': 'array', '... | [
{"role": "system", "content": "You are an assistant with access to browser debugging tools. You can use the following tools:
1. `open_browser(url: str)`: Opens a new browser tab to the specified URL. Use this when the user asks to navigate to a webpage.
2. `get_network_requests(filter_url: str = null, method: ... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'name': 'detect-emotion', 'description': 'Detect emotion from the message and decide if bot should respond.', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['msg'], 'properties': {'msg': {'type': 'string'}}, 'additionalProperties': False}}", "{'type': 'function',... | [
{
"role": "user",
"content": "I need help understanding the refund policy for a recent charge on my account."
},
{
"id": "call_kbwh55d1ku92t",
"type": "function",
"function": {
"name": "get-support-response",
"arguments": {'topic': 'bill... | INCORRECT | PARAM_VALUE_ERROR | ['The user query explicitly asks about 'refund policy', but the incorrect parameter for 'category' is 'refounds', which is a subtle typo. The system expects 'refunds' to accurately match the user's request.'] |
["{'type': 'function', 'function': {'name': 'calculate', 'description': 'Calculates/evaluates the given expression.', 'parameters': {'properties': {'expression': {'type': 'string', 'title': 'Expression'}}, 'required': ['expression']}}}", "{'type': 'function', 'function': {'name': 'add', 'description': 'Add two numbers'... | [
{
"role": "user",
"content": "What is the result of the following calculation: (15 + 5) * 4 / 2?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_s2q9jaj9vfc",
... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'type': 'function', 'function': {'name': 'get_championship_standings', 'description': 'Get Formula One championship standings', 'parameters': {'properties': {'year': {'type': 'number', 'description': 'Season year (e.g., 2023)'}, 'round_num': {'type': 'number', 'description': 'Round number (optional, gets latest stan... | [
{
"role": "user",
"content": "Can you show me the qualifying results for the 2022 Monaco Grand Prix?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_oj5m2ux2x6l7sc9... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'type': 'function', 'function': {'name': 'addToSupermemory', 'description': 'Store user information, preferences, and behaviors in Supermemory. Use this to remember important context about the user.', 'parameters': {'properties': {'thingToRemember': {'type': 'string', 'description': 'The information to store in memo... | [
{"role": "system", "content": "You are an assistant with access to a powerful memory system. You can store new information and retrieve existing information using the following tools:
1. `addToSupermemory(content: str, tags: list[str])`: Use this tool to store new facts, observations, or pieces of information. P... | INCORRECT | PARAM_VALUE_ERROR | ['The 'content' parameter incorrectly states the deadline as 'December 15th', but the user's query clearly specifies 'November 15th'. This is a one-word difference leading to a significant factual error.'] |
["{'type': 'function', 'function': {'name': 'search_crypto', 'description': '\\n Search for coins, categories and markets.\\n\\n Args:\\n query: Search query string\\n ', 'parameters': {'properties': {'query': {'type': 'string', 'title': 'Query'}}, 'required': ['query']}}}", '{\'type\': \'function\', \'... | [
{
"role": "user",
"content": "Can you give me all the detailed information about Bitcoin, like its market cap and current supply?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role"... | INCORRECT | PARAM_VALUE_ERROR | ['The 'coin_id' parameter in the incorrect call is misspelled as 'bitcoiin' instead of 'bitcoin'. This subtle typo (an extra 'i') would prevent the tool from finding the correct cryptocurrency data, as it requires the exact identifier 'bitcoin'.'] |
['{\'type\': \'function\', \'function\': {\'name\': \'getFigjamContent\', \'description\': \'Get content from a Figjam board. \\n\\nExample URL: https://www.figma.com/board/{file-id}/{board-name}?node-id={node-id}\\n\\nThe URL format is:\\n- Base: https://www.figma.com/board/\\n- File ID: The string after /board/ and b... | [
{"role": "system", "content": "You are an AI assistant designed to interact with Figma/FigJam files. You have access to the following tools:
- `getFigjamContent(fileId: string)`: Retrieves the entire content of a specified FigJam file. Use this when the user asks for a complete overview, export, or all data from... | INCORRECT | PARAM_VALUE_ERROR | ['The 'fileId' in the incorrect parameters ('9876543210fedcba99') differs from the one specified in the user's query ('9876543210fedcba98') by a single digit. Additionally, the 'nodeType' 'STICKIES' is plural, whereas the user's request for 'sticky notes' typically implies the singular type 'STICKY' for tool definition... |
["{'name': 'mcp_reed_jobs_search_jobs', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['keywords'], 'properties': {'contract': {'type': 'boolean'}, 'fullTime': {'type': 'boolean'}, 'keywords': {'type': 'string'}, 'partTime': {'type': 'boolean'}, 'permanent': {'type'... | [
{"role": "system", "content": "You are an AI assistant designed to help users find jobs using the mcp_reed_jobs_search_jobs tool. This tool allows you to search for job vacancies based on various criteria. You should call mcp_reed_jobs_search_jobs when a user explicitly asks to find jobs, providing details such a... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly requested jobs within a '10-mile radius', but the 'radiusInMiles' parameter in the tool call was incorrectly set to '11', which is an off-by-one mismatch.'] |
["{'type': 'function', 'function': {'name': 'get_crypto_price', 'description': 'Get the current price of a cryptocurrency', 'parameters': {'properties': {'crypto_id': {'type': 'string', 'title': 'crypto_id', 'default': 'bitcoin'}, 'vs_currency': {'type': 'string', 'title': 'vs_currency', 'default': 'usd'}}, 'required':... | [
{
"role": "user",
"content": "Could you please give a warm greeting to Sarah?"
},
{
"id": "call_ock4l3v5yj",
"type": "function",
"function": {
"name": "get_greeting",
"arguments": {'name': 'Sara'}
}
}
] | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly requested to greet 'Sarah', but the 'name' parameter in the tool call is subtly incorrect as 'Sara', missing the 'h' at the end.'] |
["{'type': 'function', 'function': {'name': 'echo', 'description': 'Echoes back the message provided', 'parameters': {'properties': {}, 'required': []}}}", "{'type': 'function', 'function': {'name': 'echo', 'description': 'Echoes back the input message', 'parameters': {'properties': {'message': {'type': 'string', 'desc... | [
{"role": "system", "content": "You are an assistant with access to a tool called 'echo'. This tool can be used to repeat any given message back to the user. Use the 'echo' tool whenever the user asks you to simply repeat or confirm a specific piece of text or information. The tool requires a single parameter, 'me... | INCORRECT | PARAM_VALUE_ERROR | ['The 'message' parameter in the incorrect tool call has a subtle typo ('reservaton' instead of 'reservation'), which does not exactly match the string provided in the user's query.'] |
["{'name': 'ask_agent', 'description': 'Ask a question to a specific DB agent', 'inputSchema': {'type': 'object', 'required': ['agent_id', 'question'], 'properties': {'agent_id': {'type': 'string', 'title': 'Agent Id'}, 'question': {'type': 'string', 'title': 'Question'}}}}", "{'name': 'get_db_credentials', 'descriptio... | [
{
"role": "user",
"content": "Can you show me the five most recent pending orders with an amount greater than 100 dollars from the customer transactions database? I need their order ID, amount, and customer ID."
},
{
"id": "call_9wuldefd923c73g",
"type": "function",
... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly requested 'the five most recent pending orders', but the 'query' parameter in the incorrect tool call specifies 'LIMIT 4', which would only retrieve four orders instead of the requested five. This is an off-by-one error.'] |
['{\'name\': \'send_audio_message\', \'description\': \'Send any audio file as a WhatsApp audio message to the specified recipient. For group messages use the JID. If it errors due to ffmpeg not being installed, use send_file instead.\\n \\n Args:\\n recipient: The recipient - either a phone number with co... | [
{"role": "system", "content": "You are an advanced AI assistant capable of interacting with the Omni Memory Interface (OMI) for managing conversations and memories, processing UMB commands, tracking progress, and updating context. You can also manage and debug configuration files, migrate file naming, and switch ... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'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 assistant for power system analysis. You have access to several tools to manage and analyze power networks.
- `load_network(network_id: str, version: Optional[str] = None)`: Use this tool to load an existing power network by its unique identifier. If a specific version of... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
['{\'name\': \'get-prerequisites\', \'description\': \'Get all prerequisites data from OnSecurity for a specific round. Prerequisites are requirements that need to be fulfilled before a security assessment can begin.\', \'inputSchema\': {\'type\': \'object\', \'$schema\': \'http://json-schema.org/draft-07/schema#\', \'... | [
{
"role": "user",
"content": "Can you show me all the high severity open findings for project DEV-P-987?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly requested findings for 'project DEV-P-987'. However, the 'project_id' parameter in the tool call was incorrectly set to 'DEV-P-988', which is a one-digit difference from the user's specified project identifier and would retrieve data for a different project.'] |
["{'type': 'function', 'function': {'name': 'execute-command', 'description': 'Execute a shell command and return the output.', 'parameters': {'properties': {'command': {'type': 'string', 'description': 'The command to execute'}}, 'required': ['command']}}}", '{\'name\': \'add-memory\', \'description\': \'Add a new mem... | [
{"role": "system", "content": "You are an AI assistant capable of generating images based on user requests. When a user asks to create or generate an image, you should use the `generateImage` tool. This tool requires a `prompt` describing the image content, a `size` specifying the desired resolution (e.g., '1024x... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
['{\'type\': \'function\', \'function\': {\'name\': \'get_editor_state\', \'description\': "Retrieve the current state of the Unity Editor, including active GameObjects, selection state, play mode status, scene hierarchy, and project structure. This tool provides a comprehensive snapshot of the editor\'s current contex... | [
{
"role": "user",
"content": "Can you check if there have been any critical errors in the system logs recently?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
... | INCORRECT | PARAM_VALUE_ERROR | ['The 'log_type' parameter 'systam' has a single letter typo ('a' instead of 'e') compared to the user's request for 'system' logs. This subtle difference makes the parameter invalid.'] |
['{\'name\': \'search_entity\', \'description\': \'\\n Search for a Wikidata entity ID by its query.\\n\\n Args:\\n query (str): The query to search for. The query should be unambiguous enough to uniquely identify the entity.\\n\\n Returns:\\n str: The Wikidata entity ID corresponding to the give... | [
{"role": "system", "content": "You are an AI assistant designed to interact with a knowledge graph using a suite of specialized tools. Your goal is to accurately interpret user requests and call the appropriate tool(s) with correct parameters. Always prioritize using the most specific tool available for a given t... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly asked for 'Elvis Presley'. The correct entity ID for Elvis Presley is 'Q355'. The provided incorrect entity ID 'Q356' refers to a different entity (e.g., 'Battle of the Somme' in Wikidata), which does not match the user's request, despite being a valid ID format.'] |
["{'type': 'function', 'function': {'name': 'execute_command', 'description': 'Execute a shell command on the current platform', 'parameters': {'properties': {'args': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Command arguments'}, 'command': {'type': 'string', 'description': 'The command to execute'... | [
{
"role": "user",
"content": "Please approve the pending command with ID 'cmd-a4b3c2d1'."
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_kwkg5q2dgtzaa0lyw9q7aahde",... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'name': 'aim-security-prompt-tool', 'description': 'Security Prompt Enhancement Tool', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['user_prompt'], 'properties': {'user_prompt': {'type': 'string', 'description': 'The original user prompt to enhance with securit... | [
{"role": "system", "content": "You have access to two specialized tools: 'aim-security-prompt-tool' and 'ai-safety-guard'. Use 'aim-security-prompt-tool' when the user's request involves crafting, analyzing, or refining a prompt related to cybersecurity, threat detection, or security awareness. This tool helps ev... | INCORRECT | PARAM_VALUE_ERROR | ['The 'threat_category' parameter is incorrectly spelled as 'fishiing'. The user explicitly states 'phishing attempt' in their query, which requires the correct spelling 'phishing'.'] |
["{'type': 'function', 'function': {'name': 'get-historical-analysis', 'description': 'Get historical price analysis with customizable timeframe', 'parameters': {'properties': {'days': {'type': 'number', 'default': 7, 'description': 'Number of days to analyze (1-30)'}, 'symbol': {'type': 'string', 'description': 'Crypt... | [
{
"role": "user",
"content": "Could you provide a daily summary of the cryptocurrency market today?"
},
{
"id": "call_n8ljb78rgfkijqbtm",
"type": "function",
"function": {
"name": "get-market-analysis",
"arguments": {'report_type': 'dail... | INCORRECT | PARAM_VALUE_ERROR | ['The 'report_type' parameter 'dailly_summary' contains a subtle typo ('ll' instead of 'l') and should be 'daily_summary' to match the intended report type requested by the user.'] |
["{'type': 'function', 'function': {'name': 'calculate', 'description': 'Calculates/evaluates the given expression.', 'parameters': {'properties': {'expression': {'type': 'string', 'title': 'Expression'}}, 'required': ['expression']}}}", "{'type': 'function', 'function': {'name': 'add', 'description': 'Add two numbers'... | [
{
"role": "user",
"content": "Can you add 42 and 118 for me?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_fhotas1o6nb4ndxv8ppe04mtjw",
"name": "a... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
["{'name': 'nsfw', 'description': 'Validate if an image is NSFW', 'inputSchema': {'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'URL for the image input.'}, 'file_store_key': {'type': 'string', 'description': 'Optional file store key.'}}}}", '{\'type\': \'function\', \'f... | [
{"role": "system", "content": "You are an assistant with access to several system monitoring tools. Use these tools to retrieve information as requested by the user.
- `pgrep(process_name: str, user: Optional[str] = None, full_command: Optional[bool] = False)`: Find process IDs (PIDs) based on process name or fu... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'type': 'function', 'function': {'name': 'get_incident', 'description': 'Get details of a specific incident', 'parameters': {'properties': {'incident_id': {'type': 'number', 'description': 'Incident ID'}}, 'required': ['incident_id']}}}", "{'type': 'function', 'function': {'name': 'get_organization', 'description': ... | [
{
"role": "user",
"content": "Could you please fetch the details for the organization with the ID 'corp_ABC_456'?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
... | INCORRECT | PARAM_VALUE_ERROR | ['The 'organization_id' in the incorrect parameters is 'corp_ABC_457', which is an off-by-one numerical difference from 'corp_ABC_456' specified in the user's query.'] |
["{'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": "The assistant has access to the following tools:
- `city-locator(city_name: str)`: Use this tool to find geographical details or information about a specific city when the user asks for it.
- `get_timeline_summary(user_id: str)`: Use this tool to get a high-level summary of a user's... | INCORRECT | PARAM_VALUE_ERROR | ['The incorrect parameters contain two subtle errors. The `author_id` "blogMaste" is missing the final 'r' from "blogMaster" as specified in the user query (1 letter difference). Additionally, the `limit` is set to 9, whereas the user explicitly requested "the last 10 posts" (off-by-one difference).'] |
['{\'type\': \'function\', \'function\': {\'name\': \'get-monitors\', \'description\': "Fetch monitors from Datadog with optional filtering. Use groupStates to filter by monitor status (e.g., \'alert\', \'warn\', \'no data\'), tags or monitorTags to filter by tag criteria, and limit to control result size.", \'paramete... | [
{
"role": "user",
"content": "Could you search for all metrics related to 'aws.ec2'?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
"stop_reason": "to... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'type': 'function', 'function': {'name': 'install_mcp', 'description': 'Install the MCP server on your local machine. You can install the MCP server with configuration.', 'parameters': {'properties': {'client': {'enum': ['cursor', 'claude', 'windsurf', 'cline', 'enconvo', 'witsy'], 'type': 'string', 'description': '... | [
{"role": "system", "content": "You are an AI assistant with access to several tools. Use them judiciously to fulfill user requests.
- `sendMessage(recipient: string, content: string)`: Sends a direct message to a user or channel. Provide the recipient identifier and the message text.
- `createAssistantMessage(thr... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
["{'name': 'query-models', 'description': 'Query multiple AI models via Ollama and get their responses to compare perspectives', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['question'], 'properties': {'models': {'type': 'array', 'items': {'type': 'string'}, 'desc... | [
{"role": "system", "content": "You are an AI assistant capable of interacting with a `query-models` tool. This tool allows you to retrieve detailed information about available AI models. When a user asks for information about a specific AI model, its versions, or its operational status, you should call the `query... | INCORRECT | PARAM_VALUE_ERROR | ['The `model_id` 'gemini-prox' is incorrect; the user specified 'Gemini Pro' without the 'x'. The `version` 'v1.6' does not match the requested 'version 1.5'. Finally, 'prodcution' for `status` contains a subtle typo, as the user clearly asked for models 'in production'.'] |
["{'type': 'function', 'function': {'name': 'getLoomComments', 'description': 'Get comments from a Loom video URL', 'parameters': {'properties': {'videoUrl': {'type': 'string', 'description': 'The Loom video URL (e.g., https://www.loom.com/share/123456)'}}, 'required': ['videoUrl']}}}", "{'type': 'function', 'function'... | [
{
"role": "user",
"content": "Can you please fetch the transcript for the Loom video with the ID 'e8a7f9c2d1'?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
... | INCORRECT | PARAM_VALUE_ERROR | ['The user clearly specified the Loom ID 'e8a7f9c2d1', but the incorrect parameters provide 'e8a7f9c2d0', which is a one-digit difference from the requested ID.'] |
["{'name': 'get_adset_by_id', 'description': '$2a', 'inputSchema': {'type': 'object', 'title': 'get_adset_by_idArguments', 'required': ['adset_id'], 'properties': {'fields': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'title': 'Fields', 'default': None}, 'adset_id': {'type': 'string', ... | [
{"role": "system", "content": "You are a helpful assistant with access to various tools. Use `google_search` for general information. Use `get_forecast(latitude: number, longitude: number)` to retrieve the weather forecast for specific geographical coordinates. Use `get_alerts(state: string)` to get weather alert... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
["{'type': 'function', 'function': {'name': 'todoist_rename_shared_labels', 'description': 'Rename one or more shared labels in Todoist', 'parameters': {'properties': {'name': {'type': 'string', 'description': 'The name of the existing label to rename'}, 'labels': {'type': 'array', 'items': {'type': 'object', 'required... | [
{"role": "system", "content": "You are a helpful assistant with access to several specialized tools. Use these tools to fulfill user requests efficiently and accurately. Here are the tools at your disposal:
- get_relevant_docs: To retrieve documentation or information.
- track_analytics: To record or analyze usag... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'name': 'digBlock', 'description': 'Dig a block at the specified coordinates', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['x', 'y', 'z'], 'properties': {'x': {'type': 'number', 'description': 'X coordinate'}, 'y': {'type': 'number', 'description': 'Y coordina... | [
{
"role": "user",
"content": "Please equip the iron helmet on my head."
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_q44vpr4wxfis7v1kr",
"name": "... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
['{\'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 AI assistant designed to provide nutritional details for various fruits. When a user asks about the nutritional content, calorie count, vitamin information, or any other health-related data for a specific fruit, you should use the `get_fruit_nutrition` tool. This tool req... | INCORRECT | PARAM_VALUE_ERROR | ['The 'fruit_name' parameter in the incorrect tool call uses 'aple' instead of 'apple', which is a subtle one-letter typo. The user's query clearly specified 'apple', but the incorrect parameter misses the second 'p', making it invalid for the requested fruit.'] |
["{'name': 'create_scheduled_email_send_at_specific_time', 'description': '$20', 'inputSchema': {'type': 'object', 'title': 'create_scheduled_email_send_at_specific_timeArguments', 'required': ['title', 'subject', 'body', 'minutes', 'hours', 'mdays', 'months', 'wdays'], 'properties': {'body': {'type': 'string', 'title'... | [
{
"role": "user",
"content": "Please remove all log entries from the 'logs' collection in the 'prod_db' database where the status is 'ARCHIVED'."
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
["{'name': 'read_query', 'description': 'Execute a SELECT query.', 'inputSchema': {'type': 'object', 'required': ['query'], 'properties': {'query': {'type': 'string', 'description': 'SELECT SQL query to execute'}}}}", "{'name': 'append_insight', 'description': 'Add a data insight to the memo', 'inputSchema': {'type': '... | [
{
"role": "user",
"content": "Can you fetch all sales data for the East region that occurred after January 1st, 2023, from our sales database?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly asked for sales data based on 'sales date', implying a field named 'sales_date'. The incorrect parameter 'sales_data' in the filter conditions is a subtle one-letter difference that might refer to a different data column or cause an error due to an invalid column name, deviating from the intended ... |
["{'name': 'search', 'description': 'Search barnsworthburning.net for the given query', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['query'], 'properties': {'query': {'type': 'string', 'minLength': 2, 'description': 'The search query to look for on barnsworthburn... | [
{"role": "system", "content": "You are an AI assistant with access to a 'search' tool. The 'search' tool can be used to find information on the internet. To use the 'search' tool, you must provide a `query` string, which is the specific question or keywords you want to search for. You can also optionally specify ... | INCORRECT | PARAM_VALUE_ERROR | ['The 'max_results' parameter is incorrect. The user explicitly asked for 'just one good result', which corresponds to a `max_results` of 1. The incorrect parameters specify `max_results` as 2, which is an off-by-one mismatch with the user's precise request.'] |
["{'name': 'qdrant-find', 'description': 'Look up memories in Qdrant. Use this tool when you need to: \\n - Find memories by their content \\n - Access memories for further analysis \\n - Get some personal information about the user', 'inputSchema': {'type': 'object', 'title': 'findArguments', 'required': ['query'], 'p... | [
{
"role": "user",
"content": "Please remember that my anniversary is on July 22nd."
},
{
"type": "function_call",
"id": "call_repdhb9snx6ey0sbrg9ygbyn1y",
"name": "qdrant-store",
"arguments": {'information': 22072024, 'metadata': 'anniversary'}
}
] | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
['{\'name\': \'send_webhook\', \'inputSchema\': {\'type\': \'object\', \'$schema\': \'http://json-schema.org/draft-07/schema#\', \'required\': [\'url\', \'method\'], \'properties\': {\'url\': {\'type\': \'string\', \'description\': \'URL do webhook (ex: https://meuwebhook.com.br)\'}, \'method\': {\'enum\': [\'GET\', \'... | [
{
"role": "user",
"content": "Could you please pull the sales performance data for the third quarter directly from our CRM database?"
},
{
"id": "call_azxhjnuc2lqxig0umf",
"type": "function",
"function": {
"name": "read_query",
"argument... | INCORRECT | PARAM_VALUE_ERROR | ['The 'query_id' in the incorrect parameters is 'sales_performanc_q3', which contains a subtle typo (missing the 'e' at the end of 'performance'). The user's query clearly refers to 'sales performance data', implying the full and correct spelling of 'performance'.'] |
["{'name': 'list_directory', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['path'], 'properties': {'path': {'type': 'string', 'description': 'Directory path to list'}}, 'additionalProperties': False}}", "{'name': 'check_port', 'inputSchema': {'type': 'object', '$sc... | [
{"role": "system", "content": "You are an AI assistant designed to interact with BigQuery data. You have access to the following tools:
- `get_table_details(dataset_id: str, table_id: str)`: Retrieves the schema and other details for a specific table within a BigQuery dataset.
- `execute_bigquery_sql(sql_query: s... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
["{'type': 'function', 'function': {'name': 'Add File', 'description': 'Add a file or website from a URL to Hyperspell.', 'parameters': {'properties': {'url': {'type': 'string', 'title': 'Url'}}, 'required': ['url']}}}", "{'type': 'function', 'function': {'name': 'Add Memory', 'description': 'Add a plain text document ... | [
{
"role": "user",
"content": "Please remember that the new server password is 'AlphaBravoCharlie123!'. You can title this memory 'Server Credentials'."
},
{
"id": "call_gq9r8honjh4r7237tsw13gvrwy9oas",
"type": "function",
"function": {
"name": "Add ... | INCORRECT | PARAM_VALUE_ERROR | ['incorrect data type'] |
["{'type': 'function', 'function': {'name': 'speech-to-text', 'description': 'Convert speech to text, powered by JigsawStack', 'parameters': {'properties': {'url': {'type': 'string', 'description': 'URL for the audio input.'}, 'language': {'type': 'string', 'description': 'Language of the audio.'}, 'translate': {'type'... | [
{"role": "system", "content": "You are a helpful assistant with access to a set of tools to manage and query system resources. Your goal is to accurately answer user questions by intelligently selecting and calling the appropriate tools. If a tool call is needed, provide the tool name and its parameters.
Avail... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'name': 'search_pages', 'description': 'Search pages from Bookstack', 'inputSchema': {'type': 'object', 'properties': {'page': {'type': 'number', 'default': 1, 'minimum': 1, 'description': 'Page number to return'}, 'count': {'type': 'number', 'default': 10, 'maximum': 30, 'minimum': 1, 'description': 'Number of page... | [
{"role": "system", "content": "You are a helpful assistant equipped with several tools.
Use the `search_pages` tool when the user asks for factual information, current data, or general knowledge that might be found online or in a document database.
Use the `getSecondOpinion` tool when the user explicitly requ... | INCORRECT | PARAM_VALUE_ERROR | ['The incorrect 'current_approach' parameter contains a subtle typo: 'side affects' instead of the correct 'side effects'. 'Effects' (noun) refers to the results or consequences, which is appropriate for describing outcomes of medication, while 'affects' (verb) means to influence. This is a common but incorrect substit... |
["{'type': 'function', 'function': {'name': 'assess-site', 'description': 'This system evaluates the compliance and potential risks associated with web crawling activities. It is designed to assist developers, legal teams, and data professionals in ensuring that their crawlers operate within acceptable technical, legal... | [
{"role": "system", "content": "The 'assess-site' tool is designed to evaluate various aspects of a given website. You should use this tool when the user explicitly asks to check, analyze, evaluate, or assess a website for its security, performance, or accessibility. The tool requires two parameters: 'url' (the fu... | INCORRECT | PARAM_VALUE_ERROR | ['The 'url' parameter in the incorrect tool call contains a subtle typo ('gooogle.com' instead of 'google.com'), which does not accurately reflect the user's request to assess 'Google's main website'.'] |
["{'name': 'fetch_website_nested', 'description': 'Fetch website content with nested URL crawling and convert to clean markdown', 'inputSchema': {'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The starting URL to fetch and crawl'}, 'timeout': {'type': 'number', 'default'... | [
{
"role": "user",
"content": "Could you please retrieve the results for the poll with ID 9876? I need the data from November 1st, 2023, to November 15th, 2023."
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"typ... | INCORRECT | PARAM_VALUE_ERROR | ['contextually inappropriate'] |
['{\'type\': \'function\', \'function\': {\'name\': \'read_docx\', \'description\': "Read complete contents of a docx file including tables and images.Use this tool when you want to read file endswith \'.docx\'.Paragraphs are separated with two line breaks.This tool convert images into placeholder [Image].\'--- Paragra... | [
{"role": "system", "content": "You are an AI assistant designed to help users manage Microsoft Word documents. You have access to the following tools:
- `read_docx(file_path: str)`: Reads the content of a specified .docx file and returns its text. Use this when the user asks to view, retrieve, or get information ... | INCORRECT | PARAM_VALUE_ERROR | ['The 'file_path' in the incorrect parameters has a different file extension (.doc instead of .docx), implying an older Word document format which the 'read_docx' tool might not be designed to handle or which might not exist, failing to match the user's specific request for a modern '.docx' file.'] |
["{'type': 'function', 'function': {'name': 'get_crypto_price', 'description': '', 'parameters': {'properties': {'coin_id': {'type': 'string', 'title': 'Coin Id'}}, 'required': ['coin_id']}}}"] | [
{"role": "system", "content": "You have access to the `get_crypto_price` tool. Use this tool to retrieve the current market price of a cryptocurrency. Call `get_crypto_price(symbol: str, fiat_currency: str)` when a user asks for the price of a specific cryptocurrency and specifies the fiat currency they want the ... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly asked for 'Solana', but the `symbol` was incorrectly specified as 'SOLN' (a one-letter difference, plausible typo). Furthermore, the user requested the price in 'US Dollars' (fiat currency), but the `fiat_currency` was incorrectly set to 'USDT', which is a stablecoin, not a fiat currency.'] |
["{'name': 'push_files', 'description': 'Push multiple files to a GitLab project in a single commit', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['project_id', 'branch', 'files', 'commit_message'], 'properties': {'files': {'type': 'array', 'items': {'type': 'obje... | [
{"role": "system", "content": "You have access to the tool `get_context(query: string)`. This tool is designed to retrieve specific contextual information or documents based on a search query. Use it when the user asks for details, reports, data, or any information that requires looking up existing knowledge. The... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'name': 'add', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['a', 'b'], 'properties': {'a': {'type': 'number'}, 'b': {'type': 'number'}}, 'additionalProperties': False}}"] | [
{
"role": "user",
"content": "Can you please add five and three for me?"
},
{
"id": "call_yjukek4lfsy6o6zz",
"type": "function",
"function": {
"name": "add",
"arguments": {'number1': '5', 'number2': '4'}
}
}
] | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly requested to add 'five and three'. The incorrect parameters provide '5' and '4' instead of '5' and '3', which is an off-by-one error for the second number requested by the user.'] |
['{\'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 55.75 on groceries today, October 26th. Can you log that as an expense for my weekly shop?"
},
{
"id": "call_xmebs1r55azyvpga3",
"type": "function",
"function": {
"name": "create_transaction",
"argum... | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly stated an amount of '55.75'. However, the 'amount' parameter in the incorrect tool call is '55.57', which is a subtle two-digit swap or typo, making it numerically incorrect despite being close.'] |
["{'name': 'get_trending_videos', 'description': 'Fetch trending YouTube videos.', 'inputSchema': {'type': 'object', 'title': 'get_trending_videosArguments', 'properties': {'max_results': {'type': 'string', 'title': 'max_results', 'default': 30}, 'region_code': {'type': 'string', 'title': 'region_code', 'default': 'US'... | [
{
"role": "user",
"content": "Show me the top 5 trending videos in Great Britain."
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_ks0dtl4iiid1gd2c1rwj91wsa",
... | INCORRECT | PARAM_VALUE_ERROR | ['wrong data type'] |
["{'type': 'function', 'function': {'name': 'generateVideoFromImage', 'description': 'Generate a video from an image', 'parameters': {'properties': {'image': {'anyOf': [{'type': 'object', 'required': ['type', 'mimeType', 'data'], 'properties': {'data': {'type': 'string', 'minLength': 1}, 'type': {'type': 'string', 'con... | [
{
"role": "user",
"content": "Could you please retrieve the image with the ID `img_abc123def456` for me?"
},
{
"type": "function_call",
"id": "call_wbihwavgsm9ve",
"name": "getImage",
"arguments": {'image_id': 'img_abc123def457'}
}
] | INCORRECT | PARAM_VALUE_ERROR | ['The user explicitly requested the image with ID `img_abc123def456`. The incorrect parameters provide `img_abc123def457`, which is a one-digit difference, making it refer to a different image ID that was not specified by the user.'] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.