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': 'describe_project', 'description': 'Describes a Neon project', 'parameters': {'properties': {'params': {'type': 'object', 'required': ['projectId'], 'properties': {'projectId': {'type': 'string', 'description': 'The ID of the project to describe'}}, 'additionalProperties': Fa... | [
{
"role": "user",
"content": "How can I check the current billing cycle and usage for my Neon account?"
},
{
"role": "assistant",
"content": "I don’t have permission to access that."
}
] | CORRECT | VALID_CALL | None |
["{'name': 'prem_upload_document', 'description': 'Upload a document to a Prem AI repository', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['repository_id', 'file_path'], 'properties': {'file_path': {'type': 'string', 'description': 'Path to the file to upload'}, ... | [
{
"role": "user",
"content": "Can you book a flight for me to New York next week?"
},
{
"role": "assistant",
"content": "This request exceeds my current capabilities."
}
] | CORRECT | VALID_CALL | None |
["{'name': 'render-website-screenshot', 'description': 'Renders a screenshot of a website and returns it as an image or a JSON with the cache URL (preferred for full-page screenshots).', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['url'], 'properties': {'url': {'... | [
{
"role": "user",
"content": "Could you please take a screenshot of Google's homepage for me? I need it to be 1280 by 720 pixels and in PNG format."
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_us... | CORRECT | VALID_CALL | None |
['{\'type\': \'function\', \'function\': {\'name\': \'write-research-file\', \'description\': "Write research content to a file. This tool allows you to save research findings, documentation, or any text content to a specified file path.\\n\\n SECURITY: File writing is controlled by environment varia... | [
{"role": "system", "content": "You are an AI assistant equipped with a tool named `get_rss`. This tool is designed to fetch the content of an RSS feed from a specified URL. You should invoke `get_rss` whenever a user requests to retrieve information from an RSS feed or provides an RSS feed URL and asks for its co... | CORRECT | VALID_CALL | None |
["{'name': 'calculate-bmi', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['weightKg', 'heightCm'], 'properties': {'heightCm': {'type': 'number', 'maximum': 300, 'minimum': 0}, 'weightKg': {'type': 'number', 'maximum': 500, 'minimum': 0}}, 'additionalProperties': Fa... | [
{
"role": "user",
"content": "Could you calculate my BMI? I weigh 70 kg and my height is 175 cm."
},
{
"id": "call_oop34d7anenxsfu2myj2hlmi8bdk8",
"type": "function",
"function": {
"name": "calculate-bmi",
"arguments": {'weight_kg': 70, ... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'get_trace', 'description': 'Get trace information and metrics by trace_id.', 'parameters': {'properties': {'trace_id': {'type': 'string', 'description': 'Trace ID'}}, 'required': ['trace_id']}}}", "{'type': 'function', 'function': {'name': 'auth', 'description': 'Authorize u... | [
{
"role": "user",
"content": "Could you fetch the summary for the trace identified as `8f3b2a9e-5c1d-4e7a-8f0b-2c3d4e5f6a7b`?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"i... | CORRECT | VALID_CALL | None |
["{'name': 'youtube_transcription', 'description': 'Extracts transcription from a Youtube video provided by the user', 'inputSchema': {'type': 'object', 'required': ['link'], 'properties': {'link': {'type': 'string', 'description': 'Youtube video link'}}}}", '{\'type\': \'function\', \'function\': {\'name\': \'unzip\',... | [
{"role": "system", "content": "You are a cryptocurrency data assistant. You have access to the following tools to provide information to the user:
1. **API-coins-list**: Use this to get a comprehensive list of all supported cryptocurrencies and their IDs. This is useful when the user is asking about a coin and ... | CORRECT | VALID_CALL | None |
['{\'type\': \'function\', \'function\': {\'name\': \'search_stock\', \'description\': \'This tool is meant to search stocks but just returns a practical joke.\\nArgs:\\n stock_ticker: a stock ticker symbol that will be ignored\\n Example payload: "AAPL"\\n\\nReturns:\\n str: A practical joke\\n Example Res... | [
{
"role": "user",
"content": "Can you recommend a good Italian restaurant near me?"
},
{
"role": "assistant",
"content": "That’s beyond what I can access at the moment."
}
] | CORRECT | VALID_CALL | None |
['{\'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": "user",
"content": "Please retrieve the transcript for the Granola meeting with the ID 'abc123-fake-id-456-def789'."
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "a... | CORRECT | VALID_CALL | None |
["{'name': 'text-translation', 'description': 'Translate text quickly and easily with JigsawStack, we support over 180+ language pairs.', 'inputSchema': {'type': 'object', 'required': ['text', 'target_language'], 'properties': {'text': {'type': 'string', 'description': 'Text in current langauge.'}, 'target_language': {... | [
{
"role": "user",
"content": "Can you summarize this document for me?"
},
{
"role": "assistant",
"content": "Unfortunately, that’s outside my scope of knowledge."
}
] | CORRECT | VALID_CALL | None |
["{'name': 'markdownify', 'description': '\\n Convert a webpage into clean, formatted markdown.\\n\\n Args:\\n website_url: URL of the webpage to convert\\n\\n Returns:\\n Dictionary containing the markdown result\\n ', 'inputSchema': {'type': 'object', 'title': 'markdownifyArguments', 'requir... | [
{"role": "system", "content": "You are a helpful assistant with access to the following tools:
- "echo(text: string)": Repeats the given text back to the user. Useful for simple acknowledgements or debugging.
- "calculate-bmi(weight_kg: float, height_m: float)": Calculates the Body Mass Index (BMI) given a perso... | CORRECT | VALID_CALL | None |
['{\'name\': \'search_pubmed\', \'description\': "Search academic papers from PubMed.\\n\\n Args:\\n query: Search query string (e.g., \'machine learning\').\\n max_results: Maximum number of papers to return (default: 10).\\n Returns:\\n List of paper metadata in dictionary format.\\n ", ... | [
{
"role": "user",
"content": "Find me the top 5 papers on arXiv about 'transformer models in computer vision'."
},
{
"id": "call_82zhykxg15dz7dtn9wxcq24dal030",
"type": "function",
"function": {
"name": "search_arxiv",
"arguments": {'que... | CORRECT | VALID_CALL | None |
["{'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'}}}}"] | [
{
"role": "user",
"content": "Can you tell me how to prepare a classic lasagna?"
},
{
"id": "call_xdskjpc7oosaqvw6qra0w",
"type": "function",
"function": {
"name": "search_meal",
"arguments": {'meal_name': 'classic lasagna'}
}
... | CORRECT | VALID_CALL | None |
["{'name': 'getRelations', 'description': 'Get relations for a collection', 'inputSchema': {'type': 'object', 'required': [], 'properties': {'url': {'type': 'string', 'description': 'Directus API URL (default from config)'}, 'token': {'type': 'string', 'description': 'Authentication token (default from config)'}, 'coll... | [
{
"role": "user",
"content": "Can you list all the relationships for the 'articles' collection?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
"stop_r... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'analogicalReasoning', 'description': 'A detailed tool for analogical thinking between source and target domains.\\nThis tool helps models structure analogies systematically to improve understanding and reasoning.\\nIt facilitates explicit mapping between domains, inference g... | [
{
"role": "user",
"content": "Can you book me a flight from New York to London for next Tuesday?"
},
{
"role": "assistant",
"content": "I cannot answer that with the information I have."
}
] | CORRECT | VALID_CALL | None |
["{'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": "user",
"content": "Can you provide me with comprehensive information about the IP address 8.8.8.8, including its geolocation and any open ports?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": ... | CORRECT | VALID_CALL | None |
["{'name': 'get-balance-of-address', 'description': 'Get the balance for a MultiversX address', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['address'], 'properties': {'address': {'type': 'string', 'description': 'The bech32 representation of the address'}}, 'addi... | [
{"role": "system", "content": "You are an AI assistant specialized in domain name management and general knowledge. You have access to the following tools:
- `gemini-thinking`: Use this tool for general reasoning, calculations, or when no other specific tool is suitable for the user's request.
- `search-expired-d... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'rpc_discover', 'description': 'This uses JSON-RPC to call `rpc.discover` which is part of the OpenRPC Specification for discovery for JSON-RPC servers. A user would prompt: What JSON-RPC methods does this server have? <server url>', 'parameters': {'properties': {'server': {'... | [
{"role": "system", "content": "You are a helpful assistant with access to several tools. Use the `rpc_discover` tool to find out what JSON-RPC methods a server has, given its URL. Use `rpc_call` to make a JSON-RPC call. Use `get_figma_data` to retrieve data from Figma. Use `get-product-details` to get detailed in... | CORRECT | VALID_CALL | None |
["{'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'}}}}", '{\'name... | [
{
"role": "user",
"content": "Please create a new run for the assistant on thread_abc_456 using access token your_access_token_123 and assistant ID asst_xyz_789."
},
{
"id": "call_nemswgyud2ysml",
"type": "function",
"function": {
"name": "createAss... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'analogicalReasoning', 'description': 'A detailed tool for analogical thinking between source and target domains.\\nThis tool helps models structure analogies systematically to improve understanding and reasoning.\\nIt facilitates explicit mapping between domains, inference g... | [
{"role": "system", "content": "You are an AI assistant designed to help users explore museum collections. You have access to the following tools:
- `search-museum-objects(query: str, department: str = None, era: str = None, artist: str = None, limit: int = 10)`: Use this tool to search for objects within the muse... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'search-news', 'description': 'Search for news articles from The Verge by keyword', 'parameters': {'properties': {'days': {'type': 'number', 'description': 'Number of days to look back (default: 30)'}, 'keyword': {'type': 'string', 'description': 'Keyword to search for in new... | [
{"role": "system", "content": "You are an AI assistant with access to several tools. Use these tools to respond to user queries accurately and efficiently.
Here are the tools and how to use them:
1. **search-news(query: string)**: Use this tool to find the latest news articles or headlines related to a specifi... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'delete_observations', 'description': 'Delete specific observations from entities in the knowledge graph', 'parameters': {'properties': {'deletions': {'type': 'array', 'items': {'type': 'object', 'required': ['entityName', 'observations'], 'properties': {'entityName': {'type'... | [
{"role": "system", "content": "You have access to the `convert_document` tool. Use this tool to convert a document from its current format to a specified target format. This is useful when a user requests a document in a different file type, for example, converting a PDF to a DOCX, or an ODT to a PDF. Always spec... | CORRECT | VALID_CALL | None |
["{'name': 'score_solution', 'description': 'Score a solution against a specific consistency check.\\n\\nUse this tool to evaluate how well a solution performs against each consistency check.\\nScores should be between 0.0 (poor) and 1.0 (excellent).\\n\\nThe LLM should evaluate the solution content against the consist... | [
{"role": "system", "content": "You are an expert assistant designed to help with repository analysis and penetration testing methodologies. You have access to the following tools:
- "pentestthinkingMCP()": Provides guidance or insights related to penetration testing methodologies and best practices. Use this when... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'get_file_behavior_summary', 'description': '\\n Name: get_file_behavior_summary\\n Description: Retrieves a summary of all behavior reports (sandbox execution details) for a specific file hash (MD5/SHA-1/SHA-256). This provides a consolidated view of dynamic analysis r... | [
{
"role": "user",
"content": "What are the top 10 cryptocurrencies by market cap?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_6kpsll0sj09xrdnztr9s8w65",
... | CORRECT | VALID_CALL | None |
["{'name': 'list_directory', 'description': 'List the contents of a directory', 'inputSchema': {'type': 'object', 'required': ['path'], 'properties': {'path': {'type': 'string', 'description': 'Path to the directory to list'}}}}", "{'name': 'create_directory', 'description': 'Create a new directory', 'inputSchema': {'t... | [
{
"role": "user",
"content": "Can you search for all text files in the '/home/user/documents' directory, but exclude any files that start with 'temp' or 'archive_'?"
},
{
"id": "call_xi3tb7ync87emz",
"type": "function",
"function": {
"name": "search... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'exchange_oauth_code', 'description': 'Exchange an OAuth authorization code for an access token\\n \\n Args:\\n code: The authorization code received from the redirect\\n redirect_uri: The same redirect URI used in the authorization request\\n ', 'param... | [
{
"role": "user",
"content": "Can you fetch the full details for the podcast episode with ID ep_45678?"
},
{
"type": "function_call",
"id": "call_69ejvh0j07rug",
"name": "get_episode_details_tool",
"arguments": {'episode_id': 'ep_45678'}
}
] | CORRECT | VALID_CALL | None |
["{'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']}}}", "{'name': 'getLoomTranscript', '... | [
{"role": "system", "content": "You are a helpful assistant with access to a suite of tools for managing and retrieving information from a Confluence-like system and other platforms. Use these tools to answer user queries accurately and efficiently. Available tools include: getLoomComments, getLoomTranscript, get_... | CORRECT | VALID_CALL | None |
["{'name': 'execute_code', 'description': 'Execute code in a secure sandbox environment.', 'inputSchema': {'type': 'object', 'properties': {'payload': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Payload', 'default': None}, 'filepath': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Filepath'... | [
{
"role": "user",
"content": "Could you please write and execute a Python script to compute the factorial of the number 5?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assi... | CORRECT | VALID_CALL | None |
["{'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": "system", "content": "You are an AI assistant designed to manage smart home devices. You have access to the following tool:
- "get_node_status(node_id: str)": Use this tool to retrieve the current operational status of a specific smart home device node. The `node_id` is a unique identifier for the device... | CORRECT | VALID_CALL | None |
["{'name': 'generate_intune_remediation_script', 'description': '$20', 'inputSchema': {'type': 'object', 'title': 'generate_intune_remediation_scriptArguments', 'required': ['description', 'remediation_logic'], 'properties': {'timeout': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Timeout', 'default': 6... | [
{
"role": "user",
"content": "What's the capital of Australia and what's its population?"
},
{
"role": "assistant",
"content": "I do not have access to that information."
}
] | CORRECT | VALID_CALL | None |
['{\'name\': \'getAlerts\', \'description\': \'Get current alerts for national parks including closures, hazards, and important information\', \'inputSchema\': {\'type\': \'object\', \'$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?"
},
{
"id": "call_or0lliote9c7n6zcdwi4",
"type": "function",
"function": {
"name": "getAlerts",
"arguments": {'parkCode': 'YELL', 'type': 'closure... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'connect_database', 'description': 'Connect to a specific ClickHouse database', 'parameters': {'properties': {'database': {'type': 'string', 'title': 'Database'}}, 'required': ['database']}}}", "{'name': 'execute_query', 'description': 'Execute ClickHouse queries', 'inputSche... | [
{
"role": "user",
"content": "Can you show me the top 5 best-selling products from the sales database for the entire month of January 2023?"
},
{
"id": "call_pgqnlfo24b",
"type": "function",
"function": {
"name": "execute_query",
"argume... | CORRECT | VALID_CALL | None |
["{'name': 'fund-account', 'description': 'Fund a Stellar account with testnet lumens.', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['address'], 'properties': {'address': {'type': 'string', 'description': 'The Stellar address to fund'}}, 'additionalProperties': F... | [
{
"role": "user",
"content": "Send the document at '/path/to/invoice.pdf' to the group chat '123456789-987654321@g.us'."
},
{
"type": "function_call",
"id": "call_bes3b",
"name": "send_file",
"arguments": {'recipient': '123456789-987654321@g.us', 'media... | CORRECT | VALID_CALL | None |
["{'name': 'get_meta_platform_id', 'description': 'Given a company or brand name, return the Meta Platform ID for the brand.', 'inputSchema': {'type': 'object', 'required': ['brand_name'], 'properties': {'brand_name': {'type': 'string', 'title': 'Brand Name'}}}}", "{'name': 'get_meta_ads', 'description': 'Given a Meta ... | [
{
"role": "user",
"content": "Could you please get me all the currently running ad campaigns for the Meta platform identified by ID 1234567890?"
},
{
"type": "function_call",
"id": "call_rsiai1fb2vmzsqnpfl4",
"name": "get_meta_ads",
"arguments": {'platf... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'transfer_funds', 'description': 'Transfer funds to another Stellar wallet', 'parameters': {'properties': {'asset': {'type': 'string', 'description': 'Asset to transfer (defaults to XLM)'}, 'amount': {'type': 'string', 'description': 'Amount to transfer'}, 'secretKey': {'type... | [
{"role": "system", "content": "You are a financial assistant equipped with several tools to help users manage their accounts. Use these tools appropriately based on user requests.
- 'transfer_funds(source_account_id: string, destination_account_id: string, amount: number, currency: string)': Use this tool to ini... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'retrieve_list_of_messages_in_user_chats', 'description': 'Retrieve list of messages in a user chats with parallel request', 'parameters': {'properties': {'user_chat_ids': {'type': 'array', 'items': {'type': 'string'}}}, 'required': ['user_chat_ids']}}}", "{'type': 'function'... | [
{
"role": "user",
"content": "Can you please tell me how many unread messages I have?"
},
{
"role": "assistant",
"content": "I'm sorry, but I don't have that information."
}
] | CORRECT | VALID_CALL | None |
["{'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": "What are the 5 latest uploads from my subscribed channels?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_3rb42gt3e1s3j6apbbqhx14bqpg... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'write_dofile', 'description': 'write the stata-code to dofile', 'parameters': {'properties': {'content': {'type': 'string', 'title': 'Content'}}, 'required': ['content']}}}", "{'type': 'function', 'function': {'name': 'read_log', 'description': '\\n Read the log file and ... | [
{"role": "system", "content": "You are an expert Stata assistant capable of managing and executing Stata scripts and analyzing Stata output. You have access to the following tools:
- `write_dofile(filename: str, content: str)`: Use this to create a new Stata `.do` file with the specified content. The `filename` s... | CORRECT | VALID_CALL | None |
["{'name': 'metacognitiveMonitoring', 'description': 'A detailed tool for systematic self-monitoring of knowledge and reasoning quality.\\nThis tool helps models track knowledge boundaries, claim certainty, and reasoning biases.\\nIt provides a framework for metacognitive assessment across various domains and reasoning... | [
{
"role": "user",
"content": "Could you please retrieve the statistics, such as subscriber count, total views, and video count, for the YouTube channels with these IDs: 'UC-lHJZR3Gqxm24_Vd_AJ5Yw' and 'UC8-Th83bH_thdKZDJCrn88g'?"
},
{
"id": "call_k64riesb6yfo02xdty1",
"... | CORRECT | VALID_CALL | None |
['{\'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": "Can you give me statistics about the HTML pages in the sitemap located at https://example.com/sitemap.xml?"
},
{
"type": "function_call",
"id": "call_66sku",
"name": "get_sitemap_stats",
"arguments": {'sitemap_url': 'https:... | CORRECT | VALID_CALL | None |
['{\'name\': \'collect_research\', \'description\': \'\\n Collect comprehensive research data on any topic using Gemini AI and web search.\\n\\n Performs intelligent web research with multiple search strategies, iterative\\n refinement, and source verification. Returns structured data for synthesis.\\n\\n A... | [
{"role": "system", "content": "You are an AI assistant capable of interacting with a Jira system. You have access to the following tools:
1. **jira_search(project: str = None, status: str = None, assignee: str = None, summary_contains: str = None, issue_type: str = None):** This tool allows you to search for Ji... | CORRECT | VALID_CALL | None |
["{'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": "system", "content": "You are an AI assistant designed to help users manage information efficiently using a set of specialized tools. Always select the most appropriate tool based on the user's intent.
Available tools:
- **Add File(file_name, content, mime_type)**: Use this tool to store new files or do... | CORRECT | VALID_CALL | None |
["{'name': 'git_summary', 'description': '\\n\\tGet a summary of a GitHub repository that includes \\n\\t\\t- Repo name, \\n\\t\\t- Files in repo\\n\\t\\t- Number of tokens in repo\\n\\t\\t- Summary from the README.md\\n\\n\\tArgs:\\n\\t\\towner: The GitHub organization or username\\n\\t\\trepo: The repository name\\n\... | [
{
"role": "user",
"content": "I have completed task 'task-efg-456' for request 'req-abc-123'. Please mark it as done. The requested changes have been implemented and pushed to the main branch."
},
{
"type": "function_call",
"id": "call_uuek0w73nhra8ewvyl3rtzi8y",
... | CORRECT | VALID_CALL | None |
["{'name': 'remove_background', 'description': 'Remove background in the input image using Recraft.\\nThis operation takes an input image and returns the same image with detected background removed. Raster image will be always returned.\\nLocal path or URL to resulting image and its preview will be returned in the resp... | [
{
"role": "user",
"content": "Run an aggressive Nmap scan against the host 192.168.1.1."
},
{
"id": "call_5n5c6wgs6f3ck",
"type": "function",
"function": {
"name": "nmapScan",
"arguments": {'target': '192.168.1.1', 'flags': '-A'}
... | CORRECT | VALID_CALL | None |
["{'name': 'get-company-info', 'description': 'Get detailed company information', 'inputSchema': {'type': 'object', 'required': ['symbol'], 'properties': {'symbol': {'type': 'string', 'description': 'Stock symbol (e.g., AAPL, MSFT)'}}}}", "{'name': 'get-crypto-exchange-rate', 'description': 'Get current cryptocurrency ... | [
{"role": "system", "content": "You are a helpful assistant with access to several tools. Use `fetch_news_headlines_by_query` when the user asks for news headlines related to a specific topic or keyword. Use `fetch_latest_news_headlines` when the user requests the most recent news headlines without specifying a to... | CORRECT | VALID_CALL | None |
['{\'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\'}}}}', "{'name': 'get_u... | [
{
"role": "user",
"content": "Can you help me with real-time CRUD suggestions? Our Java/Kotlin root package is `com.mycompany.app`."
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"rol... | CORRECT | VALID_CALL | None |
['{\'type\': \'function\', \'function\': {\'name\': \'find_products_to_buy\', \'description\': "Find current products to buy on Amazon with real prices and purchase links. Use this tool when users ask: \'what should I buy\', \'product recommendations\', \'shopping suggestions\', \'find me products\', \'hot items\', \'g... | [
{"role": "system", "content": "You are a helpful assistant equipped with specialized tools to assist with various tasks.
Available tools:
- `generate_memory_bank_template()`: Use this tool to create a structured template for a memory bank, useful for organizing information related to specific topics or projects.... | CORRECT | VALID_CALL | None |
['{\'type\': \'function\', \'function\': {\'name\': \'get_deep_directory_tree\', \'description\': \'Get deep directory tree\', \'parameters\': {\'properties\': {\'path\': {\'type\': \'string\', \'description\': \'Path to get the directory tree (preferably absolute path)\'}, \'options\': {\'type\': \'object\', \'default... | [
{
"role": "user",
"content": "Can you generate a directory tree for the path '/usr/local/apps', going down 4 levels and excluding any 'cache' or '.log' directories?"
},
{
"type": "function_call",
"id": "call_dtndyeu4i7j9dxey8n9tn5csd87xiq",
"name": "get_deep_di... | CORRECT | VALID_CALL | None |
['{\'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].\'--- Paragraph [number] ---\' is indicator of each ... | [
{"role": "system", "content": "You are an AI assistant designed to help users by interacting with various tools.
* **`get-related-address(street_address: str, city: str, state: str, postal_code: str)`**: Use this tool to find information about addresses related to a given location. This is useful for tasks like... | CORRECT | VALID_CALL | None |
["{'name': 'get_pubmed_count', 'description': '\\n Get the number of PubMed results for multiple search terms.\\n \\n This function queries PubMed and returns the count of results for each provided search term.\\n Useful for comparing the prevalence of different medical terms or concepts in the literature.\... | [
{
"role": "user",
"content": "Can you find the 5 most recent articles about 'atrial fibrillation treatment' in the 'New England Journal of Medicine'?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'get_order', 'description': 'Get an order by ID', 'parameters': {'properties': {'order_id': {'type': 'string', 'description': 'The ID of the order'}}, 'required': ['order_id']}}}", "{'type': 'function', 'function': {'name': 'get_product_variants', 'description': 'Get all vari... | [
{"role": "system", "content": "You are an AI assistant specialized in research and documentation. Use `deep-research-tool` when the user asks for extensive information gathering on a specific topic, requiring web searches, crawling, and aggregation of data. Use `write-research-file` when the user requests to save... | CORRECT | VALID_CALL | None |
['{\'type\': \'function\', \'function\': {\'name\': \'download_article\', \'description\': "\\nDownload the article hosted on arXiv.org as a PDF file. This tool searches for the article based on its \\ntitle, retrieves the article\'s PDF, and saves it to a specified download location using the arXiv ID as \\nthe filena... | [
{"role": "system", "content": "You are an AI assistant designed to help users navigate and retrieve information from arXiv. You have access to the following tools:
- `search_arxiv(query: str)`: Searches arXiv for articles based on keywords, author names, or article titles. Use this when the user is looking for ar... | CORRECT | VALID_CALL | None |
['{\'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 PDF - optional, default is "A4" (e.g. "A4... | [
{"role": "system", "content": "You are an AI assistant designed to provide weather information. You have access to the following tools:
- `get_weather_summary(location: str)`: Provides a brief summary of the weather for a given location.
- `get_weather_by_coordinates(latitude: float, longitude: float)`: Retrieves... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'fly-status', 'description': 'Get status of a Fly.io app', 'parameters': {'properties': {'app': {'type': 'string', 'description': 'Name of the app'}}, 'required': ['app']}}}", "{'type': 'function', 'function': {'name': 'fly-logs', 'description': 'Get logs for a Fly.io app or ... | [
{"role": "system", "content": "You are an assistant with access to tools for managing Fly.io applications.
- Use the 'fly-status' tool to check the current deployment status, health, and general information about a specific application. This tool is appropriate when a user asks about an application's operational... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'list_dns_records', 'description': 'List all DNS records for the configured zone', 'parameters': {'properties': {'name': {'type': 'string', 'description': 'Filter by record name (optional)'}, 'type': {'enum': ['A', 'AAAA', 'CNAME', 'MX', 'TXT', 'NS', 'SRV', 'CAA', 'PTR'], 'ty... | [
{"role": "system", "content": "You are an AI assistant with access to several tools. Your goal is to assist the user by selecting and utilizing the most appropriate tool for their request. Carefully consider the user's intent and the capabilities of each tool.
- `sleep(duration: int)`: Pauses execution for a spe... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'spotify-play', 'description': 'Play a specific track by ID or URI', 'parameters': {'properties': {'trackId': {'type': 'string', 'description': 'Spotify track ID or URI (spotify:track:xxxx)'}}, 'required': ['trackId']}}}", "{'name': 'spotify-find-playlist', 'description': 'Fi... | [
{
"role": "user",
"content": "Play the song with Spotify track ID spotify:track:11dFghVXANMlKmJXsNCbNl."
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_uod0ho6vk32f... | CORRECT | VALID_CALL | None |
["{'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": "user",
"content": "Can you please provide the financial statements for PTT stock in Thailand from 2021 to 2023?"
},
{
"type": "function_call",
"id": "call_4ytsohhhldrojehgc3vyif",
"name": "get_financial_statement",
"arguments": {'symbol': 'PT... | CORRECT | VALID_CALL | None |
["{'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?"
},
{
"id": "call_kg2pxg9to3rkbh430h7",
"type": "function",
"function": {
"name": "execute_query",
"arguments": {'query_string'... | CORRECT | VALID_CALL | None |
["{'name': 'get_rooms_sales', 'annotations': {'title': 'Get Room Sales', 'readOnlyHint': True, 'openWorldHint': True, 'idempotentHint': True, 'destructiveHint': False}, 'description': 'Get room sales data with filtering options', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'p... | [
{
"role": "user",
"content": "What are the most popular tourist attractions in Paris?"
},
{
"role": "assistant",
"content": "That’s not something I’m able to do."
}
] | CORRECT | VALID_CALL | None |
["{'name': 'generate_intune_remediation_script', 'description': '$20', 'inputSchema': {'type': 'object', 'title': 'generate_intune_remediation_scriptArguments', 'required': ['description', 'remediation_logic'], 'properties': {'timeout': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Timeout', 'default': 6... | [
{"role": "system", "content": "You are an AI assistant with access to a variety of tools. Use the following tools to assist the user:
- generate_intune_remediation_script: Generate PowerShell scripts for Intune remediation policies.
- generate_bigfix_action_script: Generate BigFix action scripts for endpoint mana... | CORRECT | VALID_CALL | None |
['{\'name\': \'get_deep_directory_tree\', \'description\': \'Get deep directory tree\', \'inputSchema\': {\'type\': \'object\', \'$schema\': \'http://json-schema.org/draft-07/schema#\', \'required\': [\'path\'], \'properties\': {\'path\': {\'type\': \'string\', \'description\': \'Path to get the directory tree (prefera... | [
{
"role": "user",
"content": "Could you show me the directory tree for my 'quarterly_reports' folder? I'd like to see up to three levels of subdirectories."
},
{
"type": "function_call",
"id": "call_8f3cbl5lmoadqe20b6mgeske8d2",
"name": "get_deep_directory_tree... | CORRECT | VALID_CALL | None |
['{\'name\': \'search_stock\', \'description\': \'This tool is meant to search stocks but just returns a practical joke.\\nArgs:\\n stock_ticker: a stock ticker symbol that will be ignored\\n Example payload: "AAPL"\\n\\nReturns:\\n str: A practical joke\\n Example Response: "haha jokes on your, no stock ti... | [
{"role": "system", "content": "You are an AI assistant designed to play games. You have access to the 'rock_paper_scissors' tool. When a user wants to play, use this tool. The 'rock_paper_scissors' tool requires a single parameter: 'choice', which must be either 'rock', 'paper', or 'scissors'. Always choose one o... | CORRECT | VALID_CALL | None |
["{'name': 'keep-session-alive', 'description': 'Verify and refresh the current authentication token (also used for token-based authentication)', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'token': {'type': 'string', 'description': 'Optional: Provide a token t... | [
{"role": "system", "content": "You are a helpful assistant capable of interacting with various tools to provide information about products and brands, and to perform market research. Use `get_brand_detail` to get specific details about a brand, `get_product_detail` to retrieve information about a product, `search... | CORRECT | VALID_CALL | None |
["{'name': 'crawl_docs', 'description': 'Start crawling enabled docs', 'inputSchema': {'type': 'object', 'properties': {'force': {'type': 'boolean', 'description': 'Whether to force re-crawl all docs, ignoring previous crawl records'}}}}", "{'name': 'build_index', 'description': 'Build search index for docs', 'inputSch... | [
{
"role": "user",
"content": "Please create a new searchable index for our API documentation, and make sure it pulls content from 'https://example.com/api-docs/'."
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'timeout-test', 'description': 'Test timeout prevention by running for a specified duration', 'parameters': {'properties': {'duration': {'type': 'number', 'minimum': 10, 'description': 'Duration in milliseconds (minimum 10ms)'}}, 'required': ['duration']}}}", "{'type': 'funct... | [
{"role": "system", "content": "You are a helpful assistant with access to several tools. You should use these tools to answer user questions or perform tasks. Do not make up information.
Available tools:
- timeout-test(duration: int): This tool is used to simulate a long-running process or test tool timeout beha... | CORRECT | VALID_CALL | None |
["{'name': 'list_devices', 'description': 'List all devices in the Tailscale network', 'inputSchema': {'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['includeRoutes'], 'properties': {'includeRoutes': {'type': 'boolean', 'default': False, 'description': 'Include route informati... | [
{"role": "system", "content": "You are an assistant designed to interact with a sports data API. You have access to the following tools:
- `get_players(team_name: str = None, player_name: str = None)`: Use this tool to retrieve a list of players. You can filter by `team_name` to get players from a specific team,... | CORRECT | VALID_CALL | None |
['{\'type\': \'function\', \'function\': {\'name\': \'logic_solve\', \'description\': \'Solve a logic problem using Chain of Draft reasoning\', \'parameters\': {\'properties\': {\'problem\': {\'type\': \'string\', \'description\': \'The logic problem to solve\'}, \'approach\': {\'type\': \'string\', \'description\': "F... | [
{"role": "system", "content": "You are a helpful assistant with access to specialized tools. Use these tools to efficiently solve user problems.
Here's a guide for when to use each tool:
- `logic_solve`: Use this for problems that require logical deduction, complex reasoning, or solving puzzles where the soluti... | CORRECT | VALID_CALL | None |
["{'name': 'get_random_number', 'description': 'Generate a random number and store it in state', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'max': {'type': 'number', 'default': 100, 'description': 'Maximum value'}, 'min': {'type': 'number', 'default': 0, 'desc... | [
{
"role": "user",
"content": "Please remove the network alert identified by 'na-25a4-4f8e-bd32'."
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_r3h3s40jficryhrsvc0... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'Users Tool', 'description': 'Fetches a list of users from an external API', 'parameters': {'properties': {}, 'required': []}}}", "{'type': 'function', 'function': {'name': 'get_crypto_price', 'description': 'Get the current price of a cryptocurrency', 'parameters': {'propert... | [
{"role": "system", "content": "You are a helpful assistant with access to several tools.
- `Users Tool`: Use this for general user-related operations, like listing or managing users, when a more specific user tool isn't available.
- `get_crypto_price(symbol: str)`: Call this tool to fetch the current price of a c... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'update_message', 'description': 'Update message', 'parameters': {'properties': {'inbox_id': {'type': 'string', 'description': 'ID of inbox to update message from'}, 'add_labels': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Labels to add to message'}, 'mess... | [
{"role": "system", "content": "You are an AI assistant designed to help users retrieve documentation for various components. You have access to the following tool:
- `get_component_doc(component_name: str, version: str)`: Retrieves the official documentation for a specified component and its version. Use this too... | CORRECT | VALID_CALL | None |
["{'name': 'call-webhook', 'description': 'Call a webhook with optional `message` and `url` parameters', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'url': {'anyOf': [{'type': 'string', 'format': 'uri'}, {'anyOf': [{'not': {}}, {'type': 'string'}]}, {'type': 'n... | [
{
"role": "user",
"content": "Can you find me a good recipe for lasagna?"
},
{
"role": "assistant",
"content": "I don’t have the tools needed to fulfill this request."
}
] | CORRECT | VALID_CALL | None |
["{'name': 'search', 'description': '\\n Search DuckDuckGo and return formatted results.\\n\\n Args:\\n query: The search query string\\n max_results: Maximum number of results to return (default: 10)\\n ctx: MCP context for logging\\n ', 'inputSchema': {'type': 'object', 'title': 'searchA... | [
{
"role": "user",
"content": "What is the current status of the NASA Artemis program?"
},
{
"id": "call_hh6k6qjgbtncpv48kga3ylwjf",
"type": "function",
"function": {
"name": "duckduckgo_search",
"arguments": {'query': 'What is the curren... | CORRECT | VALID_CALL | None |
["{'name': 'get_data', 'description': '$1f', 'inputSchema': {'type': 'object', 'title': 'get_dataArguments', 'required': ['mart', 'dataset', 'attributes', 'filters'], 'properties': {'mart': {'type': 'string', 'title': 'Mart'}, 'dataset': {'type': 'string', 'title': 'Dataset'}, 'filters': {'type': 'object', 'title': 'Fi... | [
{
"role": "user",
"content": "Show me all available datasets in the ENSEMBL_MART_SNP mart."
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_kaq3waohbut",
... | CORRECT | VALID_CALL | None |
["{'name': 'get_whoop_cycles', 'description': 'Get WHOOP physiological cycle data (daily summaries) with optional date range and limit', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'number', 'default': 5, 'maximum': 50, 'minimum': 1, 'descript... | [
{
"role": "user",
"content": "Can you show me my recovery scores for the first week of January 2023, limited to 10 entries?"
},
{
"id": "call_wupponij0er4fo0oygj",
"type": "function",
"function": {
"name": "get_whoop_recovery",
"argument... | CORRECT | VALID_CALL | None |
['{\'name\': \'get-document\', \'description\': \'Get a specific Lucid document by its ID. Extract document ID from Lucid URL or use known document ID. Supports image export and AI analysis of diagrams.\', \'inputSchema\': {\'type\': \'object\', \'$schema\': \'http://json-schema.org/draft-07/schema#\', \'required\': [\... | [
{
"role": "user",
"content": "I need to analyze the diagram in the document with ID 'a1b2c3d4e5f6'. Can you do that?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant"... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'write_to_terminal', 'description': 'Writes text to the active iTerm terminal - often used to run a command in the terminal', 'parameters': {'properties': {'command': {'type': 'string', 'description': 'The command to run or text to write to the terminal'}}, 'required': ['comm... | [
{
"role": "user",
"content": "The current process seems to be hung. Could you please send a signal to stop it gracefully?"
},
{
"type": "function_call",
"id": "call_y02jud3s17pwy9tttq",
"name": "send_control_character",
"arguments": {'character': 'c', '... | CORRECT | VALID_CALL | None |
["{'name': 'zotero_get_item_children', 'description': 'Get all child items (attachments, notes) for a specific Zotero item.', 'inputSchema': {'type': 'object', 'title': 'get_item_childrenArguments', 'required': ['item_key'], 'properties': {'item_key': {'type': 'string', 'title': 'Item Key'}}}}", "{'type': 'function', '... | [
{"role": "system", "content": "You are an AI assistant designed to help users navigate and understand documents related to the cannabis and CBD industry. You have access to the following tools:
- `get_doc_summary(document_id: str)`: Use this tool to retrieve a concise summary of a specific document, given its uni... | CORRECT | VALID_CALL | None |
["{'name': 'list-projects', 'description': '$1f', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'number', 'maximum': 100, 'minimum': 1, 'description': 'Maximum number of items to return (1-100). Use this to control the response size. Useful for ... | [
{"role": "system", "content": "You are an AI assistant designed to interact with a logging system. You have access to the following tools:
1. `get_label_values(label_name: str)`: Use this tool to retrieve all unique values for a specific label name from the logging system. This is useful when the user wants to k... | CORRECT | VALID_CALL | None |
['{\'type\': \'function\', \'function\': {\'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 pent... | [
{
"role": "user",
"content": "Can you list all the nodes available in the 'n8n-nodes-base' package? Please give me up to 200 results."
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'get-forecast', 'description': 'Get weather forecast for a location', 'parameters': {'properties': {'latitude': {'type': 'number', 'maximum': 90, 'minimum': -90, 'description': 'Latitude of the location'}, 'longitude': {'type': 'number', 'maximum': 180, 'minimum': -180, 'desc... | [
{"role": "system", "content": "You have access to two tools to assist users with weather-related queries:
1. `get-forecast(location: str, days: int)`: Use this tool to get the weather forecast for a specific location for a number of upcoming days. You must provide both the `location` (e.g., 'Paris, France') and t... | CORRECT | VALID_CALL | None |
["{'name': 'is_accounting_company', 'inputSchema': {'type': 'object', 'required': ['nif'], 'properties': {'nif': {'type': 'string', 'title': 'Nif'}}}}", "{'name': 'search_companies_by_name_and_city', 'inputSchema': {'type': 'object', 'required': ['name', 'city'], 'properties': {'city': {'type': 'string', 'title': 'City... | [
{
"role": "user",
"content": "Could you please help me locate 'Global Solutions Inc.' in New York City?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'executeGraphQLOperation', 'description': 'Executes an arbitrary GraphQL query or mutation against the target API. Use introspectGraphQLSchema first to understand the available operations.', 'parameters': {'properties': {'query': {'type': 'string', 'description': 'The GraphQL... | [
{"role": "system", "content": "You are an AI assistant capable of interacting with various tools. Your capabilities include executing GraphQL operations, sending notifications to different Slack channels (general or alerts), and searching for preprints on medRxiv (by keywords or advanced criteria) and retrieving ... | CORRECT | VALID_CALL | None |
["{'name': 'youtube_transcription', 'description': 'Extracts transcription from a Youtube video provided by the user', 'inputSchema': {'type': 'object', 'required': ['link'], 'properties': {'link': {'type': 'string', 'description': 'Youtube video link'}}}}"] | [
{
"role": "user",
"content": "Can you fetch the English transcript for the YouTube video with the ID dQw4w9WgXcQ?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
... | CORRECT | VALID_CALL | None |
['{\'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": "Can you list all the pages under the '/products' section from the sitemap of 'https://www.fakewebsite.com'? Please also include their metadata and limit the result to 50 pages."
},
{
"role": "assistant",
"stop_reason": "tool_use",
... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'fetch_website_nested', 'description': 'Fetch website content with nested URL crawling and convert to clean markdown', 'parameters': {'properties': {'url': {'type': 'string', 'description': 'The starting URL to fetch and crawl'}, 'timeout': {'type': 'number', 'default': 10000... | [
{"role": "system", "content": "You have access to tools for retrieving website content.
- `fetch_website_single(url: str)`: Use this tool to retrieve the full HTML content of a single, specified URL. Provide the exact and complete URL as a string. This is suitable when the user requests content from one specific... | CORRECT | VALID_CALL | None |
['{\'type\': \'function\', \'function\': {\'name\': \'get_actions\', \'description\': \'Get all actions an actor can perform on a resource\', \'parameters\': {\'properties\': {\'actorId\': {\'type\': \'string\', \'description\': \'The ID of the actor\'}, \'actorType\': {\'type\': \'string\', \'description\': "The type ... | [
{
"role": "user",
"content": "Could you please give user 'usr_007' full read and write access to the document with ID 'doc_12345'?"
},
{
"type": "function_call",
"id": "call_zaldz008v2qw9q30co7ze4o77khe",
"name": "authorize",
"arguments": {'user_id': 'u... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'get_tweet', 'description': 'A tool to get a tweet by its id.', 'parameters': {'properties': {'id': {'type': 'string', 'description': 'Id of the tweet to get.'}}, 'required': ['id']}}}", "{'type': 'function', 'function': {'name': 'post_reply_to_tweet', 'description': 'Tool th... | [
{"role": "system", "content": "You are an AI assistant designed to manage and retrieve information about users and their interactions. You have access to the following tools:
- `read_omi_conversations(user_id)`: Use this tool to retrieve a history of past conversations for a specific user. It returns a list of co... | CORRECT | VALID_CALL | None |
["{'name': 'create-post', 'description': 'Create a new post with the provided content', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['content'], 'properties': {'content': {'type': 'string', 'maxLength': 280, 'minLength': 1, 'description': 'Content of the post (1-2... | [
{
"role": "user",
"content": "Please like post_12345."
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_7azm22fhfafbcdmkpzwny2cganrsh7",
"name": "togg... | CORRECT | VALID_CALL | None |
["{'name': 'detect-emotion', 'description': 'Detect emotion from the message and decide if bot should respond.', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['msg'], 'properties': {'msg': {'type': 'string'}}, 'additionalProperties': False}}", "{'type': 'function',... | [
{
"role": "user",
"content": "Please analyze the emotion in the following text: 'I'm so incredibly happy with the results! It's better than I could have ever imagined.'"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
... | CORRECT | VALID_CALL | None |
["{'name': 'create-post', 'description': 'Create a new post with the provided content', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['content'], 'properties': {'content': {'type': 'string', 'maxLength': 280, 'minLength': 1, 'description': 'Content of the post (1-2... | [
{"role": "system", "content": "You are an AI assistant with access to the following tools:
- create-post: Create a new post with the provided content. Input schema: {"content": "string", "imageUrl": "string"}
- update-username: Update your username.
- toggle-like: Toggle the like status of a post.
- reply-to-post... | CORRECT | VALID_CALL | None |
["{'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": "system", "content": "You are an AI assistant that can interact with a semantic layer. Use the 'create_query' tool to generate new data queries, specifying metrics, filters, and grouping. Use the 'fetch_query_result' tool to retrieve the results of a previously created query by its ID. Remember to always... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'opsgenie_create_alert', 'description': 'Create a new alert in Opsgenie', 'parameters': {'properties': {'note': {'type': 'string', 'description': 'Additional note that will be added while creating the alert'}, 'tags': {'type': 'array', 'items': {'type': 'string'}, 'descriptio... | [
{
"role": "user",
"content": "Can you show me the 5 most recent logs for alert ID 'a4b5c6d7'?"
},
{
"id": "call_lyw1w88d0undetobtbgm",
"type": "function",
"function": {
"name": "opsgenie_list_alert_logs",
"arguments": {'identifier': 'a4b... | CORRECT | VALID_CALL | None |
['{\'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 AI assistant capable of interacting with Feishu documents and performing other specialized tasks. When a user requests to modify a Feishu document, always prioritize the most efficient and appropriate tool. Use `delete_feishu_document_blocks` when the user's intent is to ... | CORRECT | VALID_CALL | None |
['{\'type\': \'function\', \'function\': {\'name\': \'validate_node_minimal\', \'description\': \'Quick validation that ONLY checks for missing required fields. Returns just the list of required fields that are missing. Fastest validation option - use when you only need to know if required fields are present. No warnin... | [
{"role": "system", "content": "You are an AI assistant with access to several tools. Use 'brave_local_search' for queries requiring geographically specific information (e.g., 'restaurants near me', 'weather in Paris'). Use 'brave_web_search' for general internet queries, current events, factual information, or br... | CORRECT | VALID_CALL | None |
['{\'name\': \'write-research-file\', \'description\': "Write research content to a file. This tool allows you to save research findings, documentation, or any text content to a specified file path.\\n\\n SECURITY: File writing is controlled by environment variables:\\n - FILE_WRIT... | [
{
"role": "user",
"content": "Can you check the current weather in London and give me the forecast for the next three days?"
},
{
"role": "assistant",
"content": "I can’t look that up for you."
}
] | CORRECT | VALID_CALL | None |
['{\'type\': \'function\', \'function\': {\'name\': \'analyze_repository\', \'description\': \'Analyzes a Git repository and generates a report using Uniquity Reporter. The analysis is performed with repo=off mode, meaning no local repository copy is created or persisted.\', \'parameters\': {\'properties\': {\'logEnabl... | [
{"role": "system", "content": "You are an AI assistant with access to a suite of specialized tools. Your purpose is to understand user requests and effectively use the available tools to provide accurate and relevant information. Do not engage in conversation or provide information that cannot be directly sourced... | CORRECT | VALID_CALL | None |
['{\'name\': \'generate_flux_image\', \'description\': "Let\'s you generate an image using the Flux model.", \'inputSchema\': {\'type\': \'object\', \'title\': \'generate_flux_imageArguments\', \'required\': [\'prompt\'], \'properties\': {\'prompt\': {\'type\': \'string\', \'title\': \'Prompt\', \'description\': \'The ... | [
{"role": "system", "content": "You are an AI assistant designed to help users by providing relevant documentation. You have access to the following tool:
- `get_relevant_docs(query: str)`: This tool retrieves relevant documentation or information based on a search query. Use this tool when the user asks for docum... | CORRECT | VALID_CALL | None |
["{'name': 'setTaskStatus', 'description': 'Set the status of a task', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['id', 'status', 'projectRoot'], 'properties': {'id': {'type': 'string', 'description': 'Task ID (can be comma-separated for multiple tasks)'}, 'file... | [
{
"role": "user",
"content": "Can you show me the git history for the main branch in this project?"
},
{
"role": "assistant",
"content": "I do not have that information available to me."
}
] | CORRECT | VALID_CALL | None |
['{\'name\': \'API-coins-list\', \'description\': \'Coins List (ID Map)\', \'inputSchema\': {\'type\': \'object\', \'$defs\': {\'Ping\': {\'type\': \'object\', \'properties\': {\'gecko_says\': {\'type\': \'string\'}}, \'additionalProperties\': True}, \'Global\': {\'type\': \'object\', \'properties\': {\'data\': {\'type... | [
{"role": "system", "content": "You are a security operations assistant. You can list existing security rules, retrieve security alerts, and look up details about specific entities like IP addresses, domains, or file hashes within Chronicle. Provide comprehensive and accurate information based on the available too... | CORRECT | VALID_CALL | None |
["{'name': 'execute_query', 'description': 'Execute a SQL query against a Metabase database', 'inputSchema': {'type': 'object', 'required': ['database_id', 'query'], 'properties': {'query': {'type': 'string', 'description': 'SQL query to execute'}, 'database_id': {'type': 'number', 'description': 'ID of the database to... | [
{
"role": "user",
"content": "Please execute this prolog program for me: 'mortal(X) :- man(X). man(socrates).'"
},
{
"type": "function_call",
"id": "call_xg93gtgy63y9jbqb241y2h11sx",
"name": "exec",
"arguments": {'program': 'mortal(X) :- man(X). man(soc... | CORRECT | VALID_CALL | None |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.