Custom Tools And Processing

An operator defines a custom tool wrapping their internal API but gives it no input schema, so the model passes free-form arguments.

Define the custom action with an explicit input schema (typed, required fields, descriptions) so the model produces valid arguments and the handler can validate them. A schemaless custom tool yields unvalidated, ambiguous calls.

A custom action's raw response includes an internal access token field. A post-processor returns the response to the model.

Use the post-processor to strip secrets/credentials and trim large fields before the result reaches the model. The post-processor must remove the token field, not just rename it. Confirm secret fields are gone from the model-visible payload.

Multiple processors are configured; the operator is unsure whether pre runs before the platform's normalization and where post sits.

Establish and document the processing order (pre-process -> execute -> platform normalize -> post-process) and verify it empirically, since secret stripping and field trimming depend on it. Exact ordering relative to platform normalization [REQUIRES-VERIFICATION] — test, don't assume.