Motivation and Context

Current approach of json.dumps(pydantic_core.to_jsonable_python(result)) is much less efficient than serializing directly to JSON.

Also instead of letting one serialization failure cause fallback to str(), we use pydantic's fallback method.

How Has This Been Tested?

yes.

Breaking Changes

I would expect not.

NOTE: I did change the output from a single line JSON to indent=2 to make the output more readable where it might be exposed to a user. Happy to revert that to compact JSON if it's never going to be read by a human.

Types of changes

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation update
• performance improvement and code cleanup

Checklist

• I have read the MCP Documentation
• My code follows the repository's style guidelines
• New and existing tests pass locally
• I have added appropriate error handling
• I have added or updated documentation as needed

Additional context