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': '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": "user",
"content": "Can you retrieve the full configuration JSON for the pipeline with ID 'pre-processing' from the 'edge_fleet' worker group in Cribl?"
},
{
"type": "function_call",
"id": "call_tt6r5jn0c1y775f",
"name": "cribl_getPipelineConfig",
... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'eval', 'description': 'Evaluate an expression', 'parameters': {'properties': {'env': {'type': 'object', 'description': 'Optional parameters map'}, 'expression': {'type': 'string', 'description': 'The expression to be evaluated'}}, 'required': ['expression']}}}", '{\'name\': ... | [
{
"role": "user",
"content": "What is the current weather in New York City?"
},
{
"type": "function_call",
"id": "call_qnjxs9p8vibp0bffo0x0gepiyt3bho",
"name": "get_current_weather",
"arguments": {'location': '40.7128,-74.0060'}
}
] | CORRECT | VALID_CALL | None |
["{'name': 'get_24hr_ticker', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'symbol': {'type': 'string', 'description': 'Trading pair symbol, e.g. BTCUSDT'}, 'symbols': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Array of multiple trading pair ... | [
{
"role": "user",
"content": "What's the trip log for trip ID 1234567?"
},
{
"type": "function_call",
"id": "call_unc25tk",
"name": "get_trip_log",
"arguments": {'trip_id': 1234567}
}
] | CORRECT | VALID_CALL | None |
['{\'name\': \'generateImageUrl\', \'description\': \'Generate an image URL from a text prompt\', \'inputSchema\': {\'type\': \'object\', \'required\': [\'prompt\'], \'properties\': {\'safe\': {\'type\': \'boolean\', \'description\': \'Whether to apply content filtering (default: false)\'}, \'seed\': {\'type\': \'numbe... | [
{"role": "system", "content": "You have access to two tools: 'generateImage' and 'generateImageUrl'. Use 'generateImage(prompt: string, size: string, quality: string)' to create a new image based on a textual description. The 'prompt' should be a detailed description of the desired image content. The 'size' param... | CORRECT | VALID_CALL | None |
['{\'type\': \'function\', \'function\': {\'name\': \'search\', \'description\': "Perform a web search using Traylinx\'s API, which provides detailed and contextually relevant results with citations. By default, no time filtering is applied to search results.", \'parameters\': {\'properties\': {\'query\': {\'type\': \'... | [
{"role": "system", "content": "You are a helpful assistant with access to several specialized tools.
- `get_character_info(name: str, franchise: str)`: Use this tool to retrieve detailed biographical and historical information about a specific character from a given media franchise. You must provide the character... | CORRECT | VALID_CALL | None |
["{'name': 'get_shards', 'description': 'Get shard information for all or specific indices', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'index': {'type': 'string', 'description': 'Optional index name to get shard information for'}}, 'additionalProperties': Fal... | [
{"role": "system", "content": "You are an AI assistant capable of interacting with various backend services. You have access to the following tools:
`get_shards`: Get information about shards.
`get_mappings`: Get mapping information.
`search`: Perform a general search.
`download_icon`: Download a specific icon.
`... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'get_definitions', 'description': '\\n Get definitions for a word.\\n ', 'parameters': {'properties': {'word': {'type': 'string', 'title': 'Word'}}, 'required': ['word']}}}", "{'type': 'function', 'function': {'name': 'metadata_search', 'description': 'Search documents ... | [
{
"role": "user",
"content": "I need to find all documents in the 'project_reports' table that are authored by 'Dr. Evelyn Reed' and have the status 'approved'. Can you please return a maximum of 15 results?"
},
{
"type": "function_call",
"id": "call_217m19hdmlh",
... | CORRECT | VALID_CALL | None |
["{'name': 'get_exchange_info', 'description': 'Get detailed information about a specific exchange.', 'inputSchema': {'type': 'object', 'required': ['exchange'], 'properties': {'vhost': {'type': 'string', 'title': 'Vhost', 'default': '/'}, 'exchange': {'type': 'string', 'title': 'Exchange'}}}}", "{'name': 'purge_queue'... | [
{"role": "system", "content": "You are a helpful home assistant. You have access to tools to interact with the smart home environment. Use 'homeassistant_list_entities' to retrieve a list of entities based on domain or a pattern. Use 'homeassistant_get_state' to get the current state of a specific entity. When us... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'get_films', 'description': '', 'parameters': {'properties': {'name': {'type': 'string', 'title': 'Name'}}, 'required': ['name']}}}", "{'name': 'get_order', 'description': 'Get an order by ID', 'inputSchema': {'type': 'object', 'required': ['order_id'], 'properties': {'order_... | [
{
"role": "user",
"content": "Please register a new webhook for my store with ID '12345'. The webhook URL should be 'https://example.com/webhook', it should listen for 'order_created' and 'order_paid' events, and use 'a-super-secret-key' as the secret."
},
{
"role": "assistant... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'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... | [
{"role": "system", "content": "You are an AI assistant with access to a wide range of tools. You can manage conversations (get, archive, assign, add comments, apply/remove tags), handle contacts and accounts (create, get, update), send messages, and retrieve team information. You are also capable of generating va... | CORRECT | VALID_CALL | None |
['{\'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": "user",
"content": "Can you list all the sticky notes and text elements from the FigJam board located at https://www.figma.com/board/asdf1234/example-board?"
},
{
"type": "function_call",
"id": "call_0a3um",
"name": "getFigjamNodes",
"argument... | CORRECT | VALID_CALL | None |
['{\'name\': \'search_resources\', \'description\': "Search across OpenHEXA resources (workspaces, datasets, pipelines).\\n\\nArgs:\\n query: Search query string\\n resource_type: Optional filter by resource type (\'workspace\', \'dataset\', \'pipeline\')\\n workspace_slug: Optional workspace slug to limit sea... | [
{
"role": "user",
"content": "Could you list all the files associated with the dataset 'product_sales_2023_data'?"
},
{
"type": "function_call",
"id": "call_t2d647y6",
"name": "list_dataset_files",
"arguments": {'dataset_id': 'product_sales_2023_data'}
... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'get-nuget-package-details', 'description': 'Get detailed information about a specific NuGet package', 'parameters': {'properties': {'name': {'type': 'string', 'minLength': 1}}, 'required': ['name']}}}", "{'type': 'function', 'function': {'name': 'search-npm-packages', 'descr... | [
{"role": "system", "content": "You are a helpful assistant with access to two tools:
1. `generate_mermaid_diagram(diagram_type: str, description: str)`: Use this tool to create various types of Mermaid diagrams. Valid `diagram_type` values include 'flowchart', 'sequence_diagram', 'class_diagram', 'state_diagram'... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'airbnb_listing_details', 'description': 'Get detailed information about a specific Airbnb listing. Provide direct links to the user', 'parameters': {'properties': {'id': {'type': 'string', 'description': 'The Airbnb listing ID'}, 'pets': {'type': 'number', 'description': 'Nu... | [
{"role": "system", "content": "You are a helpful assistant with access to various tools. Use these tools to answer user queries accurately and efficiently. Available tools include:
- 'sell-token': To sell cryptocurrency tokens.
- 'get-account-balance': To check an account's cryptocurrency balance.
- 'buy-token': ... | CORRECT | VALID_CALL | None |
["{'name': 'create_rule', 'description': 'Creates a new Semgrep rule', 'inputSchema': {'type': 'object', 'required': ['output_path', 'pattern', 'language', 'message'], 'properties': {'id': {'type': 'string', 'default': 'custom_rule', 'description': 'Rule identifier'}, 'message': {'type': 'string', 'description': 'Messa... | [
{"role": "system", "content": "You are an AI assistant designed to help manage manufacturing processes. You have access to several tools to perform your tasks.
**Tools:**
1. `mcpjam_search_mcp_spec(query: str)`: Use this tool to search for specific manufacturing control plan (MCP) specifications. Provide a conci... | CORRECT | VALID_CALL | None |
["{'name': 'fund-account', 'description': 'Fund a Stellar account with testnet lumens.', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['address'], 'properties': {'address': {'type': 'string', 'description': 'The Stellar address to fund'}}, 'additionalProperties': F... | [
{
"role": "user",
"content": "Can you check the weather forecast for tomorrow in London?"
},
{
"role": "assistant",
"content": "That data is not accessible in my current context."
}
] | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'getLiveTemperature', 'description': '\\n Get live temperature for a specific location.\\n\\n Args:\\n latitude: The latitude coordinate (e.g., 40.7128 for New York)\\n longitude: The longitude coordinate (e.g., -74.0060 for New York)\\n\\n Returns:\\n ... | [
{
"role": "user",
"content": "What is the current temperature at latitude 34.0522 and longitude -118.2437?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
... | CORRECT | VALID_CALL | None |
['{\'name\': \'get_recommendations_by_genre\', \'inputSchema\': {\'type\': \'object\', \'$schema\': \'http://json-schema.org/draft-07/schema#\', \'required\': [\'genre\'], \'properties\': {\'genre\': {\'type\': \'string\', \'description\': \'ç\\x94µè§\\x86å\\x89§ç±»å\\x9e\\x8bï¼\\x8cå¦\\x82"å\\x96\\x9cå\\x89§"ã\\x80\\x... | [
{
"role": "user",
"content": "What are the top trending TV shows right now, specifically for today?"
},
{
"type": "function_call",
"id": "call_up8r70qsuyd1o31",
"name": "get_trending_shows",
"arguments": {'time_window': 'day'}
}
] | CORRECT | VALID_CALL | None |
["{'name': 'execute', 'description': 'Execute browser automation tasks using natural language commands. This tool interprets your intent and translates it into appropriate browser actions.', 'inputSchema': {'type': 'object', 'required': ['command'], 'properties': {'command': {'type': 'string', 'description': 'Natural l... | [
{"role": "system", "content": "You are an assistant with access to a powerful 'execute' tool. This tool allows you to run shell commands on the underlying system. You should use the 'execute' tool whenever a user asks to perform a command-line operation, run a script, or interact with the file system or system pr... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'aes_decrypt', 'description': 'decrypt text with aes', 'parameters': {'properties': {'iv': {'type': 'string', 'description': 'iv, default is your-iv-01234567'}, 'key': {'type': 'string', 'description': 'decrypt key, default is your-key-0123456'}, 'mode': {'enum': ['ECB', 'CBC... | [
{"role": "system", "content": "You are an assistant specialized in cryptographic operations. You have access to tools for various hashing, encryption, decryption, encoding, and decoding tasks. When a user requests an operation, identify the correct tool and its parameters. Do not attempt to perform operations not... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'adjust-standard-report', 'description': 'Get a standard Adjust report with common metrics', 'parameters': {'properties': {'app_tokens': {'type': 'string', 'default': '', 'description': 'Comma-separated list of app tokens to include'}, 'date_range': {'type': 'string', 'defaul... | [
{"role": "system", "content": "You have access to two tools to help with reporting tasks. Use these tools carefully based on the user's request:
1. "adjust-standard-report(report_type: str, time_range: str, dimensions: list[str], filters: dict)": This tool is designed to generate or retrieve predefined standard r... | CORRECT | VALID_CALL | None |
["{'name': 'find_instances', 'description': '$20', 'inputSchema': {'type': 'object', 'properties': {'sort_by': {'type': 'string', 'title': 'Sort By', 'default': 'Price'}, 'page_num': {'type': 'integer', 'title': 'Page Num', 'default': 0}, 'sort_order': {'type': 'string', 'title': 'Sort Order', 'default': 'Descending'},... | [
{"role": "system", "content": "You are an AI assistant capable of interacting with several tools to fulfill user requests. Carefully analyze the user's intent to select the most appropriate tool and parameters.
Available tools:
- `find_instances(entity_type: str, filters: dict)`: Use this tool to search for spec... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'create_client', 'description': 'Create a new client', 'parameters': {'properties': {'name': {'type': 'string', 'description': 'Client name'}, 'note': {'type': 'string', 'description': 'Client note/description'}, 'workspaceId': {'type': 'string', 'description': 'Workspace ID'... | [
{"role": "system", "content": "You are a network configuration assistant with access to several tools for managing network rules. - `get_policy_based_forwarding_rules(zone_id: str, interface_name: str, rule_name: str)`: Use this tool to retrieve specific Policy-Based Forwarding (PBF) rules based on their associat... | CORRECT | VALID_CALL | None |
["{'name': 'generateVideoFromImage', 'description': 'Generate a video from an image', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['image'], 'properties': {'image': {'anyOf': [{'type': 'object', 'required': ['type', 'mimeType', 'data'], 'properties': {'data': {'ty... | [
{"role": "system", "content": "You are a helpful assistant with access to a variety of tools. Your capabilities include generating videos from images or text, creating and listing images, retrieving image information, performing various types of diligence (identity, legal, financial), getting geographical informa... | CORRECT | VALID_CALL | None |
["{'name': 'delete-prompt', 'description': 'Delete a prompt', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['promptId'], 'properties': {'promptId': {'type': 'string', 'description': 'ID of the prompt to delete'}}, 'additionalProperties': False}}", "{'name': 'create... | [
{"role": "system", "content": "You are a helpful assistant with access to several tools. Use them to assist the user.
- `list_orders(customer_id: str, status: Optional[str])`: Retrieves a list of customer orders. Use this when the user asks about their orders, specifying a customer ID and optionally a status lik... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'read_terminal_output', 'description': 'Reads the output from the active iTerm terminal', 'parameters': {'properties': {'linesOfOutput': {'type': 'integer', 'description': 'The number of lines of output to read.'}}, 'required': ['linesOfOutput']}}}", "{'name': 'write_to_termi... | [
{"role": "system", "content": "You are an AI assistant with access to a terminal. You can perform actions by calling tools.
Tools:
- `read_terminal_output()`: Reads the last output from the terminal. Use this when you need to see the results of a command you've executed or check the current state of the termina... | CORRECT | VALID_CALL | None |
["{'name': 'get_24hr_ticker', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'symbol': {'type': 'string', 'description': 'Trading pair symbol, e.g. BTCUSDT'}, 'symbols': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Array of multiple trading pair ... | [
{
"role": "user",
"content": "What is the general market sentiment for cryptocurrencies today?"
},
{
"role": "assistant",
"content": "That function isn’t currently supported."
}
] | CORRECT | VALID_CALL | None |
["{'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": "system", "content": "You are an AI assistant with access to a 'send_note' tool. Use this tool to send brief textual notes or messages to individuals. When a user explicitly asks to send a note, identify the intended recipient, the subject of the note, and the full content of the message. Call the 'send_... | 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": "system", "content": "You have access to the `echo_message` tool. This tool is designed to simply repeat any given text or message back to the user. Use `echo_message` when the user asks you to confirm a specific phrase, repeat information verbatim, or store a particular piece of text. Provide the exact ... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'mcpjam_search_mcp_spec', 'description': 'Search the MCP specification document for relevant content', 'parameters': {'properties': {'query': {'enum': ['Introduction', 'Core components', 'Connection lifecycle', 'Elicitation', 'Prompts', 'Resources', 'Roots', 'Sampling', 'Tool... | [
{
"role": "user",
"content": "I need a comprehensive, step-by-step plan for migrating our old database to a new cloud system. Make sure to cover critical aspects like data integrity, potential downtime, and how to roll back if something goes wrong."
},
{
"role": "assistant",
... | CORRECT | VALID_CALL | None |
['{\'name\': \'get_reference_points_by_state\', \'description\': \'\\n Get reference points for a specific state from USGS Real-Time Flood Impacts API\\n \\n Args:\\n state_id: State ID (e.g., "CA", "TX")\\n \', \'inputSchema\': {\'type\': \'object\', \'title\': \'get_reference_points_by_stateArgumen... | [
{"role": "system", "content": "You have access to the following tools:
- `add(product_name: str, brand: str, category: str, price_usd: float)`: Use this tool to add new sustainable fashion products to the inventory. Ensure all required parameters are provided."},
{
"role": "user",
"content": "... | CORRECT | VALID_CALL | None |
['{\'name\': \'start_new_session\', \'description\': \'Start a new browser session. Provide an instruction like "Go to https://example.com" or "Search for products on Amazon". Returns executionId for the session and initial page data with interactive elements and HTML markup.\', \'inputSchema\': {\'type\': \'object\', ... | [
{"role": "system", "content": "You are a helpful assistant with access to several tools. Carefully choose the best tool(s) to fulfill the user's request.
- `generateImage(prompt: str, style: str)`: Use this tool to create a new, original image based on a detailed textual prompt and a specific artistic style (e.g... | 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": "system", "content": "You are an AI assistant designed to help with code-related tasks. You have access to the following tools:
- `search_code(query: str, path: str = None)`: Searches the codebase for occurrences of the given `query`. An optional `path` can be provided to restrict the search to a specifi... | CORRECT | VALID_CALL | None |
["{'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 that can manage software deployments. You have access to the following tools:
- "getDeployments()": Use this to retrieve a list of all active or historical deployments.
- "listDeploymentFiles(deployment_id)": Use this to see all files associated with a specific ... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'list_events', 'description': 'List upcoming calendar events', 'parameters': {'properties': {'time_max': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Time Max', 'default': None}, 'time_min': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Time Min',... | [
{"role": "system", "content": "You are a helpful assistant with access to a suite of tools for Formula 1 data. Use these tools to answer user queries accurately and efficiently.
Here's how to use the available tools:
- `get_championship_standings()`: Use this to retrieve the current or historical driver and cons... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'create_query', 'description': 'Creates a query to the semantic layer. Use this tool to create a query to the semantic layer. Returns the query id which can be used to fetch the results of the query.', 'parameters': {'properties': {'limit': {'type': 'number'}, 'where': {'type... | [
{"role": "system", "content": "You are an AI assistant with access to a set of specialized tools. Use `create_query` to generate database queries. Use `fetch_query_result` to execute queries and retrieve their results. Use `markdown_to_mindmap` to convert markdown text into a mindmap visualization. For URL manage... | CORRECT | VALID_CALL | None |
["{'name': 'get-streaming-results', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['sessionId'], 'properties': {'format': {'enum': ['markdown', 'csv', 'json'], 'type': 'string', 'default': 'markdown', 'description': 'Output format'}, 'sessionId': {'type': 'string', ... | [
{"role": "system", "content": "You are an AI assistant with access to a set of drawing and website management tools. Your primary goal is to use these tools to fulfill user requests.
Available tools:
- `list_websites()`: Lists all websites currently being monitored for status and content changes.
- `check_websi... | CORRECT | VALID_CALL | None |
["{'name': 'run_command', 'description': '$22', 'inputSchema': {'type': 'object', 'required': ['command', 'cwd'], 'properties': {'cwd': {'type': 'string', 'title': 'Cwd', 'minLength': 1, 'description': 'Working directory where the command should be executed'}, 'command': {'type': 'string', 'title': 'Command', 'minLengt... | [
{
"role": "user",
"content": "I need to see a list of all database servers available for me to connect to. Please ensure the query times out after 30 seconds."
},
{
"id": "call_c0c66rvlv4fbatt8blnizpzdik83s",
"type": "function",
"function": {
"name"... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'fund-account', 'description': 'Fund a Stellar account with testnet lumens.', 'parameters': {'properties': {'address': {'type': 'string', 'description': 'The Stellar address to fund'}}, 'required': ['address']}}}", "{'type': 'function', 'function': {'name': 'get-transactions'... | [
{
"role": "user",
"content": "Can you show me the recent transactions for Stellar address GBG3W56V52LFX4F4257Y76G77777777777777777777777777777777777777777777?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'search_semantic_scholar', 'description': '\\n Search for papers on Semantic Scholar using a query string.\\n\\n Args:\\n query: Search query string\\n num_results: Number of results to return (default: 10)\\n\\n Returns:\\n List of dictionaries ... | [
{
"role": "user",
"content": "Please create a file named 'meeting_summary.txt' and put the following content into it: 'Today's meeting covered the Q3 financial report and new marketing strategies.'"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content"... | CORRECT | VALID_CALL | None |
['{\'name\': \'get_deep_directory_tree\', \'description\': \'Get deep directory tree\', \'inputSchema\': {\'type\': \'object\', \'$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": "Can you find Alice Smith in the Marketing department?"
},
{
"type": "function_call",
"id": "call_bmipz8czw28kyewl",
"name": "search_people",
"arguments": {'name': 'Alice Smith', 'department': 'Marketing'}
}
] | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'list-issues', 'description': 'List all issues for a repository', 'parameters': {'properties': {'repo': {'type': 'string', 'description': 'Repository name'}, 'owner': {'type': 'string', 'description': 'GitHub username or organization name'}}, 'required': ['owner', 'repo']}}}"... | [
{"role": "system", "content": "You are a helpful assistant for exploring cultural heritage. You have access to the following tools:
1. `get_cultural_recommendations(user_preferences: dict)`: Use this tool to get personalized cultural recommendations based on a user's interests (e.g., 'renaissance art', 'ancient ... | CORRECT | VALID_CALL | None |
['{\'name\': \'pg_execute_mutation\', \'description\': \'Execute data modification operations (INSERT/UPDATE/DELETE/UPSERT) - operation="insert/update/delete/upsert" with table and data. Examples: operation="insert", table="users", data={"name":"John","email":"john@example.com"}\', \'inputSchema\': {\'type\': \'object\... | [
{
"role": "user",
"content": "Can you show me the immediate contents of the `/var/log` directory?"
},
{
"type": "function_call",
"id": "call_3pxrkyzy2kj9dngts4b0i1h",
"name": "tree",
"arguments": {'path': '/var/log', 'depth': 1}
}
] | CORRECT | VALID_CALL | None |
["{'name': 'getLoomComments', 'description': 'Get comments from a Loom video URL', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['videoUrl'], 'properties': {'videoUrl': {'type': 'string', 'description': 'The Loom video URL (e.g., https://www.loom.com/share/123456)'... | [
{"role": "system", "content": "You are an AI assistant capable of managing email schedules. You have access to the following tools:
1. `create_scheduled_email_send_at_specific_time(recipient: str, subject: str, body: str, send_time: str)`: Schedules an email to be sent to a specified recipient at a precise date a... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'get_access_token_from_code', 'description': 'Exchange authorization code for an access token.', 'parameters': {'properties': {'code': {'type': 'string', 'title': 'Code'}}, 'required': ['code']}}}"] | [
{
"role": "user",
"content": "I've just successfully authorized my account. The authorization code I received is `authcode_alpha123beta456gamma789`. Please use this code to get my access token. The redirect URI was `https://mycoolapp.com/auth/callback`."
},
{
"type": "function... | CORRECT | VALID_CALL | None |
["{'name': 'get_biorxiv_metadata', 'description': '', 'inputSchema': {'type': 'object', 'title': 'get_biorxiv_metadataArguments', 'required': ['doi'], 'properties': {'doi': {'type': 'string', 'title': 'Doi'}}}}", "{'name': 'search_biorxiv_advanced', 'description': '', 'inputSchema': {'type': 'object', 'title': 'search_... | [
{
"role": "user",
"content": "Please go to 'https://example.com/articles', click on the element with the CSS selector '.load-more-btn', wait for 3 seconds, and then scrape the full page as a screenshot."
},
{
"role": "assistant",
"stop_reason": "tool_use",
"con... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'execute_query', 'description': 'Executes a Kusto Query Language (KQL) query against the configured Azure Data Explorer database and returns the results as a list of dictionaries.', 'parameters': {'properties': {'query': {'type': 'string', 'title': 'Query'}}, 'required': ['qu... | [
{
"role": "user",
"content": "What are the columns and their data types in the 'Errors' table?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
"stop_re... | CORRECT | VALID_CALL | None |
["{'name': 'use_tool', 'description': 'Execute a specific tool call on an MCP server.', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['qualifiedName', 'parameters'], 'properties': {'parameters': {'type': 'object', 'required': ['name'], 'properties': {'name': {'type... | [
{"role": "system", "content": "You are an AI assistant tasked with interacting with web pages using a set of specialized tools.
- Use `stagehand_navigate(url: str)` when you need to go to a specific URL.
- Use `stagehand_observe()` to gather information about the current state of the web page, such as visible t... | CORRECT | VALID_CALL | None |
["{'name': 'dump_codebase_context', 'description': 'Recursively reads text files from a specified directory, respecting .gitignore rules and skipping binary files. Concatenates content with file path headers/footers. Supports chunking the output for large codebases.', 'inputSchema': {'type': 'object', 'required': ['bas... | [
{"role": "system", "content": "You are an advanced cybersecurity analysis and threat intelligence assistant. You can perform a wide range of tasks including searching various data sources like Telegram, dark web, and compromised datasets; downloading files; analyzing threats; extracting forensic artifacts from sy... | CORRECT | VALID_CALL | None |
["{'name': 'getTimezoneInfo', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['timezone'], 'properties': {'timezone': {'type': 'string', 'description': 'Timezone to get information about (IANA timezone identifier)'}}, 'additionalProperties': False}}", "{'name': 'getC... | [
{"role": "system", "content": "You are a helpful assistant with access to several tools.
- Use `getTimezoneInfo(location: string)` to get detailed timezone information for a specified location, including current time, DST status, and offset. Call this when the user asks about timezones, current time in a specifi... | CORRECT | VALID_CALL | None |
["{'name': 'google_search', 'description': 'Run a Google search via SerpApi (Custom Search no longer needed).', 'inputSchema': {'type': 'object', 'title': 'google_searchArguments', 'required': ['query'], 'properties': {'query': {'type': 'string', 'title': 'Query'}}}}", "{'name': 'duck_search', 'description': 'Query Duc... | [
{"role": "system", "content": "You have access to web search tools: `google_search`, `duck_search`, and `brave_search`. Use `google_search` for general web queries, current events, widely known information, or when a broad range of results is preferred. Use `duck_search` when user privacy is a concern or for resu... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'create_lipsync_video_by_text', 'description': '$21', 'parameters': {'properties': {'text': {'type': 'string', 'title': 'Text', 'default': ''}, 'title': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Title', 'default': None}, 'voice': {'anyOf': [{'type': 'string'... | [
{"role": "system", "content": "You are an AI assistant capable of managing various tasks. You can create lipsync videos from text or audio, retrieve information from web URLs, and manage presentations using Slidev. Additionally, you can interact with and manage autonomous agents, including registering, listing, s... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'get-balance-of-address', 'description': 'Get the balance for a MultiversX address', 'parameters': {'properties': {'address': {'type': 'string', 'description': 'The bech32 representation of the address'}}, 'required': ['address']}}}", "{'type': 'function', 'function': {'name'... | [
{
"role": "user",
"content": "Can you list all the tokens owned by the address erd1qqqqqqqqqqqqqqqpqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqpzzx2y5qps5z?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
... | CORRECT | VALID_CALL | None |
['{\'name\': \'list-campaigns\', \'description\': "Fetches a summarized list of all campaigns, including name, ID, status, timestamps, PL value, tracking settings, daily limit, email count, and schedule information. Use this for an overview or to find a campaign ID. For full details like email copy (sequences) or the c... | [
{"role": "system", "content": "You are an AI assistant designed to help manage and analyze marketing campaigns. You have access to the following tools:
- 'list-campaigns()': Use this to retrieve a list of marketing campaigns. It can be filtered by status, sorted by various criteria (e.g., creation date, name), a... | CORRECT | VALID_CALL | None |
["{'name': 'search_youtube_videos', 'description': 'Search YouTube videos by keyword and retrieve detailed information', 'inputSchema': {'type': 'object', 'title': 'search_youtube_videosArguments', 'required': ['query'], 'properties': {'query': {'type': 'string', 'title': 'Query'}}}}", "{'name': 'get_youtube_transcript... | [
{
"role": "user",
"content": "Please create a meme for me. Use the template ID '181913649'. The first text box should say 'My code compiling without errors' and the second one should be 'Me, who has no idea what I'm doing'. Use the arial font with a max font size of 40px."
},
{
... | CORRECT | VALID_CALL | None |
['{\'name\': \'get_weather\', \'description\': \'Get current weather information for a city\', \'inputSchema\': {\'type\': \'object\', \'required\': [\'city\'], \'properties\': {\'city\': {\'type\': \'string\', \'description\': \'City name (e.g., "Istanbul", "London", "New York")\'}}}}', "{'name': 'get_exchange_rates',... | [
{"role": "system", "content": "You are a helpful assistant with access to the following tools:
1. `get_weather(location: str, unit: str = "celsius")`: Retrieves the current weather conditions for a specified location. Use this tool when the user asks about weather or temperature.
- Parameters:
- `locatio... | CORRECT | VALID_CALL | None |
["{'name': 'create_scheduled_email_send_at_specific_time', 'description': '$20', 'inputSchema': {'type': 'object', 'title': 'create_scheduled_email_send_at_specific_timeArguments', 'required': ['title', 'subject', 'body', 'minutes', 'hours', 'mdays', 'months', 'wdays'], 'properties': {'body': {'type': 'string', 'title'... | [
{"role": "system", "content": "You are a helpful assistant for managing workout routines and fitness data. You can help users create, update, and retrieve workout routines, exercise templates, workout events, and routine folders. Use the available tools to fulfill user requests related to their fitness journey."}... | CORRECT | VALID_CALL | None |
["{'name': 'create-post', 'description': 'Create a new post with the provided content', 'inputSchema': {'type': 'object', '$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 a helpful assistant with access to various tools. Use these tools to fulfill user requests accurately and efficiently.
Available tools:
- "create-post": To create a new social media post.
- "update-username": To change a user's username.
- "toggle-like": To like or unlike a ... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'list_events', 'description': 'List upcoming calendar events', 'parameters': {'properties': {'time_max': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Time Max', 'default': None}, 'time_min': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Time Min',... | [
{"role": "system", "content": "You are an expert NPM package assistant. You have access to a suite of tools to retrieve detailed information about NPM packages.
- npmLatest: Get the latest version of an NPM package.
- npmDeps: Retrieve dependency information for an NPM package.
- npmMaintenance: Get maintenance d... | CORRECT | VALID_CALL | None |
['{\'name\': \'get-token-info\', \'description\': \'Get information about a Pump.fun token\', \'inputSchema\': {\'type\': \'object\', \'$schema\': \'http://json-schema.org/draft-07/schema#\', \'required\': [\'tokenAddress\'], \'properties\': {\'tokenAddress\': {\'type\': \'string\', \'description\': "The token\'s mint ... | [
{"role": "system", "content": "You are a helpful financial assistant with access to several tools. You must select the most appropriate tool based on the user's request.
- `get-token-info(token_symbol: str)`: Use this to retrieve real-time information about a specific cryptocurrency, such as its current price, m... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'get_candlesticks', 'description': 'Get candlestick data for an OKX instrument', 'parameters': {'properties': {'bar': {'type': 'string', 'default': '1m', 'description': 'Time interval (e.g. 1m, 5m, 1H, 1D)'}, 'limit': {'type': 'number', 'default': 100, 'description': 'Number ... | [
{"role": "system", "content": "You are an AI assistant with access to a wide range of tools. You can assist with research tasks, including creating research plans, searching with keywords, fetching content, and managing research tokens and sources. You can also help with task management, such as updating the stat... | CORRECT | VALID_CALL | None |
["{'name': 'geocode-address', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['address'], 'properties': {'address': {'type': 'string', 'description': 'Full address to geocode'}}, 'additionalProperties': False}}", "{'name': 'lookup-property', 'inputSchema': {'type': '... | [
{"role": "system", "content": "You are an AI assistant designed to help users break down complex problems into manageable steps. You have access to the following tool:
- `sequentialthinking`: Use this tool to generate a step-by-step breakdown for a given problem. It requires a `problem_description` (string) detai... | CORRECT | VALID_CALL | None |
["{'name': 'get-crypto-price', 'description': 'Get current price and 24h stats for a cryptocurrency', 'inputSchema': {'type': 'object', 'required': ['symbol'], 'properties': {'symbol': {'type': 'string', 'description': 'Cryptocurrency symbol (e.g., BTC, ETH)'}}}}", "{'type': 'function', 'function': {'name': 'get-market... | [
{"role": "system", "content": "You are an AI assistant with the ability to manage user authentication flows. When a user has completed an authorization process and provides an authorization code, you can use the `get_access_token_from_code` tool to exchange that code for an access token. This is crucial for final... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'cross_check', 'description': 'Cross-check answers from multiple public LLM APIs given a prompt. To goal is to show a list of answers from different LLMs.\\n\\n Arguments:\\n prompt (str): The input prompt to send to the LLMs.\\n\\n Returns:\\n dict: A dic... | [
{"role": "system", "content": "You are an AI assistant designed to help users verify information consistency across different data points. You have access to the following tool:
1. `cross_check(item_id_1: string, item_id_2: string, comparison_type: string)`: Use this tool to compare and cross-reference two distin... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'search_specific_topic_news', 'description': 'Search for news articles from specific topics and extract their content.', 'parameters': {'properties': {'topic': {'type': 'string', 'title': 'Topic', 'default': 'top'}, 'timeout': {'type': 'integer', 'title': 'Timeout', 'default'... | [
{"role": "system", "content": "You are a news assistant that can search for articles. Use the `search_specific_topic_news` tool when the user asks for news within a broad, general category (like 'sports' or 'politics'). Use the `search_news` tool when the user provides specific keywords or a detailed phrase for t... | CORRECT | VALID_CALL | None |
["{'name': 'get_token_price', 'description': 'Get token current price', 'inputSchema': {'type': 'object', 'required': ['symbol'], 'properties': {'symbol': {'type': 'string', 'description': 'The token symbol'}}}}", "{'name': 'GetBudgetCategories', 'description': 'Retrieves all categories defined in the specified budget,... | [
{"role": "system", "content": "You are an AI assistant capable of managing cryptocurrency information and personal budgets. You have access to the following tools:
- `get_token_price(token_symbol: str, currency: str)`: Use this tool to retrieve the current market price of a specified cryptocurrency token in a giv... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'generate_meme_from_meme_template', 'description': '$20', 'parameters': {'properties': {'meme_text': {'type': 'array', 'items': {'type': 'string'}, 'title': 'Meme Text', 'description': '2 sentences that has to be on the meme image. Should be funny and contained. Should be a P... | [
{"role": "system", "content": "You are a helpful assistant with access to several tools.
- `get_current_weather(location: string)`: Retrieves the current weather conditions for a specified city or location.
- `get_weather_by_coordinates(latitude: float, longitude: float)`: Retrieves the current weather conditions... | CORRECT | VALID_CALL | None |
['{\'name\': \'get_recommendations_by_genre\', \'inputSchema\': {\'type\': \'object\', \'$schema\': \'http://json-schema.org/draft-07/schema#\', \'required\': [\'genre\'], \'properties\': {\'genre\': {\'type\': \'string\', \'description\': \'ç\\x94µè§\\x86å\\x89§ç±»å\\x9e\\x8bï¼\\x8cå¦\\x82"å\\x96\\x9cå\\x89§"ã\\x80\\x... | [
{
"role": "user",
"content": "Can I see any trailers or clips for Squid Game?"
},
{
"type": "function_call",
"id": "call_q9g2mc6s7m2jv7b8j297rkoqsm",
"name": "get_show_videos",
"arguments": {'show_title': 'Squid Game'}
}
] | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'GetBudgetCategories', 'description': 'Retrieves all categories defined in the specified budget, including category groups, names, and IDs.', 'parameters': {'properties': {'budget_id': {'type': 'string', 'description': 'The ID of the budget to fetch'}}, 'required': ['budget_i... | [
{"role": "system", "content": "You are an AI assistant designed to help users manage their finances by interacting with a budget management system. You have access to the following tools:
1. `GetBudgetCategories()`: Use this tool when the user asks about available budget categories, how expenses are categorized,... | CORRECT | VALID_CALL | None |
['{\'name\': \'get_chromium_latest_commit\', \'description\': \'\\nMCP handler to get the latest commit information for a specified file in Chromium repository\\n\\nArgs:\\n file_path (str): Relative path of the file in Chromium repository (e.g., "components/sync/service/data_type_manager.cc")\\n\\nReturns:\\n st... | [
{"role": "system", "content": "You are an assistant capable of providing information about Chromium development. You have access to the following tool:
- `get_chromium_latest_commit(component: str)`: Fetches the latest commit information for a specified Chromium component. Use this tool when a user asks for the ... | CORRECT | VALID_CALL | None |
["{'name': 'extract-components', 'description': 'Extract all components from Figma file and get all graphql queries and mutations', 'inputSchema': {'type': 'object'}}", "{'name': 'extract-one-component', 'description': 'Extract a single component from Figma file', 'inputSchema': {'type': 'object', '$schema': 'http://js... | [
{
"role": "user",
"content": "Can you check the current weather forecast for New York City?"
},
{
"role": "assistant",
"content": "I don’t have permission to access that."
}
] | CORRECT | VALID_CALL | None |
["{'name': 'fetch_user', 'description': 'Fetch user details from JSONPlaceholder API', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['userId'], 'properties': {'userId': {'type': 'integer', 'description': 'ID of the user to fetch (must be a positive integer)', 'excl... | [
{"role": "system", "content": "You are an AI assistant with access to several tools.
- To retrieve information about a user, use the `fetch_user` tool. This tool requires a `user_id` or `username` to identify the user.
- To perform mathematical computations, use the `calculate` tool. Provide a valid mathematica... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'detail', 'description': 'Get detailed information about a product', 'parameters': {'properties': {'id': {'type': 'string', 'description': 'Unique identifier of the product'}}, 'required': ['id']}}}", '{\'type\': \'function\', \'function\': {\'name\': \'search\', \'descriptio... | [
{
"role": "user",
"content": "Can you tell me how to redeem a gift card I've already purchased?"
},
{
"role": "assistant",
"content": "Sorry, I can't complete that task."
}
] | CORRECT | VALID_CALL | None |
["{'name': 'create-routine', 'description': 'Create a new workout routine in your Hevy account. Requires title and at least one exercise with sets. Optionally assign to a specific folder. Returns the complete routine details upon successful creation including the newly assigned routine ID.', 'inputSchema': {'type': 'ob... | [
{
"role": "user",
"content": "I need the full details for the exercise template with ID 'template_abc123'."
},
{
"type": "function_call",
"id": "call_yzvrdk83qmy2",
"name": "get-exercise-template",
"arguments": {'exerciseTemplateId': 'template_abc123'}
... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'laravel_docs_info', 'description': 'Provides metadata about documentation versions, including last update times and commit information.\\n\\nWhen to use:\\n- Checking documentation freshness\\n- Verifying version compatibility\\n- Understanding documentation state\\n- Troubl... | [
{
"role": "user",
"content": "Could you provide a list of all documentation files available for Laravel 10.x?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_9rv9pu... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'text-to-speech', 'description': 'Convert text to speech', 'parameters': {'properties': {'text': {'type': 'string', 'description': 'The text to convert to speech.'}, 'accent': {'type': 'string', 'description': 'Accent for the speech (SupportedAccents).'}, 'voice_clone_id': {'... | [
{
"role": "user",
"content": "Could you please say 'Hello, how are you today?' for me in a cheerful female voice?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'add', 'description': 'Add two numbers', 'parameters': {'properties': {'a': {'type': 'integer', 'title': 'A'}, 'b': {'type': 'integer', 'title': 'B'}}, 'required': ['a', 'b']}}}", "{'type': 'function', 'function': {'name': 'create_meeting', 'description': 'Create a new Zoom m... | [
{
"role": "user",
"content": "Please schedule a 60-minute team sync meeting for tomorrow, October 27th, at 10 AM EST, to review Q3 performance and plan for Q4."
},
{
"type": "function_call",
"id": "call_e02bj5w65mljvd1sdzifk3evd5n",
"name": "create_meeting",
... | CORRECT | VALID_CALL | None |
["{'name': 'fly-status', 'description': 'Get status of a Fly.io app', 'inputSchema': {'type': 'object', 'required': ['app'], 'properties': {'app': {'type': 'string', 'description': 'Name of the app'}}}}", "{'name': 'fly-logs', 'description': 'Get logs for a Fly.io app or specific machine', 'inputSchema': {'type': 'obje... | [
{
"role": "user",
"content": "Show me the top 10 free applications in the 'Games' category on the US App Store."
},
{
"type": "function_call",
"id": "call_envq42mhwijm3iycdyvl4997io",
"name": "app-store-list",
"arguments": {'collection': 'TOP_FREE_IOS',... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'multiply', 'description': 'Multiplies two numbers.', 'parameters': {'properties': {'a': {'type': 'integer', 'title': 'A', 'description': 'First number'}, 'b': {'type': 'integer', 'title': 'B', 'description': 'Second number'}}, 'required': ['a', 'b']}}}", "{'name': 'add', 'de... | [
{"role": "system", "content": "You are an AI assistant with access to a variety of tools. Your capabilities include: - Performing basic arithmetic operations like multiplication and addition. - Managing emails: sending and fetching emails. - Interacting with the npm ecosystem: getting the latest version of a pack... | CORRECT | VALID_CALL | None |
["{'name': 'getCommitHistory', 'description': 'Get commit history for the configured repository (string/string) within the last X days, focusing on actual file changes and diffs.', 'inputSchema': {'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['days'], 'properties': {'days': {'type... | [
{"role": "system", "content": "You are a helpful medical assistant. Use the 'get_articles_for_topic' tool to search for evidence-based medical articles on a given topic from patient.info. Use the 'return_full_content_for_articles' tool to retrieve the full text of articles when specific article URLs are provided.... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'image_adjust_saturation', 'description': 'Adjust image saturation', 'parameters': {'properties': {'input_path': {'type': 'string', 'description': 'Path to input image'}, 'saturation': {'type': 'number', 'maximum': 2, 'minimum': 0, 'description': 'Saturation multiplier (0.0 t... | [
{"role": "system", "content": "You are an assistant with access to a specialized tool. Your primary function is to help users by accurately identifying when to use this tool.
Tool:
- "analysis_token(text: str)": This tool is designed to perform a linguistic analysis and tokenization of a given text input. Use t... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'vt_url_report', 'description': '', 'parameters': {'properties': {'url': {'type': 'string', 'title': 'Url'}}, 'required': ['url']}}}", "{'name': 'vt_filehash_report', 'description': '', 'inputSchema': {'type': 'object', 'title': 'vt_filehash_reportArguments', 'required': ['fi... | [
{"role": "system", "content": "You are an AI assistant designed to help users find information. Use the `get_relevant_docs` tool to retrieve documents based on a user's query. This tool is useful for searching for specific information or concepts within a knowledge base. Always call `get_relevant_docs` when the u... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'get_weather_summary', 'description': '\\n Get a concise weather summary perfect for quick updates.\\n\\n Args:\\n city: City name to get weather for\\n ', 'parameters': {'properties': {'city': {'type': 'string', 'title': 'City'}}, 'required': ['city']}}}", '{... | [
{
"role": "user",
"content": "What is the current temperature in London, UK in Celsius?"
},
{
"type": "function_call",
"id": "call_thdg9h9mu93u",
"name": "get_current_weather",
"arguments": {'city': 'London', 'units': 'celsius', 'country_code': 'GB'}
... | 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 a helpful assistant with access to several tools. When a user asks you to perform a task, you should determine if any of your tools can help. Always prioritize using the most appropriate tool for the user's request.
Available tools:
- 'create-post(title: string, content: st... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'execute_sql', 'description': 'Execute an SQL query on the Dameng server', 'parameters': {'properties': {'query': {'type': 'string', 'description': 'The SQL query to execute'}}, 'required': ['query']}}}"] | [
{
"role": "user",
"content": "Could you list the last 10 users who registered after January 1st, 2023?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_co3lqmzms5lkb... | CORRECT | VALID_CALL | None |
["{'name': 'add', 'description': 'Add two numbers\\nArgs:\\n a: The first number\\n b: The second number\\nReturns:\\n The sum of the two numbers\\n', 'inputSchema': {'type': 'object', 'title': 'addArguments', 'required': ['a', 'b'], 'properties': {'a': {'type': 'integer', 'title': 'A'}, 'b': {'type': 'integer... | [
{
"role": "user",
"content": "Can you book a flight to New York for next Tuesday?"
},
{
"role": "assistant",
"content": "That question goes beyond my current limits."
}
] | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'search_stations_by_station_name', 'description': '\\n Search radio stations by name or partial name.\\n\\n Args:\\n name (str): Name or partial name of the radio station to search for\\n\\n Returns:\\n list: List of radio stations matching the search t... | [
{"role": "system", "content": "You are a helpful assistant that can search for radio stations. You can find stations by their country code or by their name."},
{
"role": "user",
"content": "Find any station called 'The Rock'."
},
{
"completion_message": {
"content":... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'eval', 'description': 'Evaluate an expression', 'parameters': {'properties': {'env': {'type': 'object', 'description': 'Optional parameters map'}, 'expression': {'type': 'string', 'description': 'The expression to be evaluated'}}, 'required': ['expression']}}}", '{\'name\': ... | [
{
"role": "user",
"content": "Can you show me the CREATE statement for the `orders` table located in the `sales` schema within the `prod` catalog?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
... | CORRECT | VALID_CALL | None |
["{'name': 'pentestthinkingMCP', 'description': 'Advanced reasoning tool with multiple strategies including Beam Search and Monte Carlo Tree Search', 'inputSchema': {'type': 'object', 'required': ['attackStep', 'attackStepNumber', 'totalAttackSteps', 'nextAttackStepNeeded'], 'properties': {'attackStep': {'type': 'strin... | [
{
"role": "user",
"content": "Can you fetch all the directories from the repository at https://github.com/torvalds/linux?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": ... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'update_rule', 'description': 'Update an existing policy rule', 'parameters': {'properties': {'rule_data': {'type': 'object', 'description': 'Updated rule configuration data'}, 'rule_name': {'type': 'string', 'description': 'Name of the rule to update'}, 'rule_type': {'type':... | [
{"role": "system", "content": "You have access to the `youtube_transcription` tool. Use this tool to retrieve the full transcript of a YouTube video when the user provides a valid YouTube video URL. The tool requires a `video_url` parameter. Always provide the full and accurate transcript when available."},
{... | CORRECT | VALID_CALL | None |
["{'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": "system", "content": "You are an AI assistant capable of interacting with a backend GraphQL API to retrieve or manipulate data. You have access to the `executeGraphQLOperation` tool. Use `executeGraphQLOperation` when a user's request requires fetching data or performing an action via a GraphQL query or ... | CORRECT | VALID_CALL | None |
['{\'name\': \'get-usage\', \'description\': \'Get cloud usage summary for multiple vendors and products\', \'inputSchema\': {\'type\': \'object\', \'$schema\': \'http://json-schema.org/draft-07/schema#\', \'properties\': {\'vendors\': {\'type\': \'array\', \'items\': {\'type\': \'string\'}, \'description\': "List of c... | [
{
"role": "user",
"content": "Can you please fetch the usage report for user 'user_abc_123' for the last month?"
},
{
"completion_message": {
"content": {
"type": "text",
"text": ""
},
"role": "assistant",
... | CORRECT | VALID_CALL | None |
["{'name': 'create_remaining_items', 'description': 'Create the remaining items after showing the example', 'inputSchema': {'type': 'object', 'required': ['boardId', 'count', 'startIndex'], 'properties': {'count': {'type': 'number', 'description': 'Number of remaining items to create'}, 'isDemo': {'type': 'boolean', 'd... | [
{"role": "system", "content": "You are an assistant capable of converting various units. You have access to the following tools:
- `convert_weight(value: float, from_unit: str, to_unit: str)`: Converts a weight (mass) from one unit to another (e.g., kilograms to pounds).
- `convert_volume(value: float, from_unit:... | CORRECT | VALID_CALL | None |
["{'name': 'get_news', 'description': 'Get the news of a stock/crypto ticker.', 'inputSchema': {'type': 'object', 'title': 'get_news_toolArguments', 'required': ['ticker'], 'properties': {'count': {'type': 'integer', 'title': 'Count', 'default': 5}, 'ticker': {'type': 'string', 'title': 'Ticker'}}}}", "{'name': 'get_pr... | [
{"role": "system", "content": "You are a helpful assistant that can provide information about stock and crypto tickers. You can fetch the latest news, retrieve current or historical prices, and even check the availability of internet domains. Use the provided tools to answer user queries concisely and accurately.... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'delete_paragraph', 'description': '\\n Delete specified paragraph from document\\n \\n Parameters:\\n - paragraph_index: Paragraph index to delete\\n ', 'parameters': {'properties': {'paragraph_index': {'type': 'integer', 'title': 'Paragraph Index'}}, 'require... | [
{"role": "system", "content": "You are a financial assistant with access to a tool to retrieve asset prices. Use the 'get_asset_price' tool to find the current price of a specified asset. The 'get_asset_price' tool requires one parameter: 'asset_name' (string), which should be the ticker symbol or common name of ... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'update_event', 'description': 'Update an existing calendar event', 'parameters': {'properties': {'end': {'type': 'string', 'description': 'New end time in ISO format'}, 'start': {'type': 'string', 'description': 'New start time in ISO format'}, 'eventId': {'type': 'string', ... | [
{"role": "system", "content": "You have access to the following tool: `think`.
`think` is used to articulate your internal thought process, reasoning, or planning before performing an action or generating a response. Use this tool when you need to explicitly state your reasoning, break down a complex problem, or ... | CORRECT | VALID_CALL | None |
['{\'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": "system", "content": "You are an assistant with the ability to speak. Use the `speak` tool when the user asks you to say something aloud, read text, or convey information verbally. The `speak` tool requires a `text` parameter which is the exact phrase or sentence you need to say."},
{
"role":... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'read_query', 'description': 'Execute a SELECT query.', 'parameters': {'properties': {'query': {'type': 'string', 'description': 'SELECT SQL query to execute'}}, 'required': ['query']}}}", "{'type': 'function', 'function': {'name': 'append_insight', 'description': 'Add a data... | [
{"role": "system", "content": "You are an AI assistant with access to the following tools:
1. `get_rss(url: str)`: This tool allows you to fetch the content from a specified RSS feed URL. Use this tool when a user asks for news, articles, or updates from a specific website or source that is known to provide an R... | CORRECT | VALID_CALL | None |
["{'type': 'function', 'function': {'name': 'generate_embeddings', 'description': 'Generate embeddings for text using a model. Supports both single strings and lists of strings.', 'parameters': {'properties': {'model': {'type': 'string', 'title': 'Model'}, 'prompt': {'anyOf': [{'type': 'string'}, {'type': 'array', 'ite... | [
{
"role": "user",
"content": "Hey, can you check if the 'gemma-2b' model is already downloaded on my system?"
},
{
"role": "assistant",
"stop_reason": "tool_use",
"content": [
{
"type": "tool_use",
"id": "call_5xe532n... | CORRECT | VALID_CALL | None |
['{\'type\': \'function\', \'function\': {\'name\': \'get_code_context\', \'description\': "Returns Complete Context of a given project directory, including directory tree, and code symbols. Useful for getting a quick overview of a project. Use this tool when you need to get a comprehensive overview of a project\'s cod... | [
{
"role": "user",
"content": "Could you get me the full details for Sentry issue `87654321` from our `api-gateway-service` project?"
},
{
"type": "function_call",
"id": "call_ilozv1eawa0fy",
"name": "get_sentry_issue",
"arguments": {'issue_id': '8765432... | CORRECT | VALID_CALL | None |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.