Compare generated tool schemas with handler validation

When Pipecat derives tool schemas from Python annotations, inspect the emitted JSON schema as well as the validated handler. An annotation can enforce a constraint inside Pydantic while the generated model-facing property remains unconstrained. The model may then propose values that satisfy its visible contract but repeatedly fail the handler. Use a supported explicit schema for a meaningful enum, or a bounded string when the field is only explanatory. Verify serialized requests and real handler invocation; unit tests that call the function directly miss this mismatch. This finding depends on the installed schema adapter and annotation shape. Applies when: generated Pipecat tool schemas and Pydantic argument validation share Python annotations. Keywords: Pipecat Pydantic Literal enum schema validation tools retry annotations