Agents And Workflows

A Python function is wrapped as a FunctionTool but its parameters lack type hints and the docstring is empty, so the generated tool schema is untyped and the agent calls it with wrong argument types.

Give tool functions precise type hints and a clear docstring (or an explicit Pydantic schema / fn_schema) so FunctionTool generates a correct JSON schema the agent can call reliably. Validate arguments against the schema before executing; untyped tools produce malformed calls.

An integrator uses ReActAgent with an LLM that has strong native tool/function calling, then fights with the ReAct text format being mis-parsed.

Use FunctionAgent (native tool calling) with models that support it for reliable structured tool calls; reserve ReActAgent for models without native function calling where reasoning is expressed as text. Match the agent type to the model's capabilities rather than defaulting blindly.

A FunctionTool calls an external API that raises a 503. The wrapper lets the exception propagate and crash the agent.run() loop instead of returning a tool result.

Catch tool execution failures and return them to the agent as a tool output describing the error (so the model can retry, choose another tool, or report), rather than letting the exception abort the agent loop. Cap retries to avoid a tool-call storm.