Autogen Tool Use And Function Calling

Operator wraps `def get_weather(city: str) -> str` as a FunctionTool and the model consistently passes city as an object instead of a string.

FunctionTool derives the input schema from the callable's type hints — explicit annotations are required for stable schemas. If the model is passing the wrong shape, tighten the schema (use Pydantic models for nested inputs) and rely on FunctionTool's validation rather than coercing in the function…

FunctionTool implementing send_invoice raises ConnectionError mid-call. Agent has reflect_on_tool_use=True.

AutoGen catches the tool exception and emits a tool result with the error message into the next model context so the model can correct or fall back. Verify the error message is observable (logged + surfaced) and does not include secrets. Do NOT swallow the exception silently — that produces a tool …

Operator registers a synchronous `def query_db(...)` that does blocking I/O and wraps it as a FunctionTool inside an AssistantAgent.

Prefer async def for tools that do I/O so AutoGen can await them without blocking the event loop. If a sync tool is unavoidable, run it through asyncio.to_thread / loop.run_in_executor. A blocking sync tool stalls the entire team's run_stream until it returns.