exp.json

[
    {
        "role": "user",
        "content": "Available tools for this task:\nTool:\n{'name': 'ask_user', 'signature': 'ask_user(prompt: str) -> str', 'docstring': 'Prompt the user for a response'}\n\nTool:\n{'name': 'call_ai', 'signature': 'call_ai(inputs: Any) -> Any', 'docstring': 'Not a pre-defined tool.'}\n\nTool:\n{'name': 'crawl_url', 'signature': 'crawl_url(url: str, max_depth: int = 2, max_links: int = 5, same_domain_only: bool = True, prefixes: list[str] | None = None) -> dict', 'docstring': 'Recursively crawl starting from a URL up to a specified depth.\\n\\nArgs:\\n    url: The URL to start crawling from\\n    max_depth: Maximum depth of recursion (default: 2)\\n    max_links: Maximum number of links to follow (default: 100)\\n    same_domain_only: Only follow links within the same domain (default: True)\\n    prefixes: List of prefixes to follow (default: None). So only links starting with these prefixes will be followed. If same_domain_only is True, it will be automatically added.'}\n\nTool:\n{'name': 'download_video', 'signature': 'download_video(url: str) -> str', 'docstring': 'download video from url and return the local path'}\n\nTool:\n{'name': 'get_weather', 'signature': \"get_weather(day: Literal['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday'], location: str) -> str\", 'docstring': 'get the weather at a day in a location'}\n\nTool:\n{'name': 'list_available_grounds', 'signature': 'list_available_grounds(location: str) -> list[str]', 'docstring': 'list all available grounds in a location'}",
        "purpose": "available_tools"
    }
]