You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Ordinary-class structured outputs discard Annotated field constraints and accept invalid values #3712
An ordinary class's Annotated field constraints disappear when its return annotation is converted into a structured output model. A field declared Annotated[int, Field(gt=0)] produces a schema with only type: integer, and an instance containing zero is accepted as structured_content={"value": 0}.
I expected the generated property to retain exclusiveMinimum: 0 and output conversion to reject zero. The reproduction first proves that Pydantic validates the exact field annotation and rejects that value, then fails because SDK conversion does not raise ValidationError. A BaseModel with the same constraint rejects zero, and the existing ordinary-class output test still passes.
This is a class-field path, separate from the string-keyed dictionary return annotation metadata loss tracked in #2935. The relevant class path calls get_type_hints(type_annotation) without retaining extras before synthesizing the model. A tool author relying on the declared bound therefore gets neither the advertised constraint nor its validation.
uv run --frozen pytest tests/server/mcpserver/test_func_metadata.py::test_ordinary_class_output_rejects_values_outside_annotated_field_bounds -q
Python & MCP Python SDK
Python 3.14.7; Pydantic 2.12.5; MCP 2.3.0 (tag v2.3.0, 2118f14f8a19bc158d8a1cf90af58d85d187f849). Also reproduced using main source at 754254c08fe1c3eda18b69da3d336106fe8d72d6.
AI-assisted investigation and test reproduction, with a human in the loop.
Looks like the cause is L540 in func_metadata.py at 754254c. The Case 4 path (dataclasses and plain annotated classes) calls get_type_hints(type_annotation) without include_extras=True, so Annotated is stripped before _create_model_from_class builds the model. The TypedDict rebuild at L595 already passes include_extras=True.
Dataclasses are affected too. On MCP 2.3.0, pydantic 2.14.1, Python 3.13, a @dataclass with value: Annotated[int, Field(gt=0)] gives {'title': 'Value', 'type': 'integer'} and convert_result accepts {'value': 0}.
Workarounds until it is fixed:
Return a TypedDict. The schema keeps exclusiveMinimum: 0, and {"value": 0} raises greater_than.
A BaseModel return keeps the schema constraint, but the returned instance is not re-validated, so model_construct(value=0) still goes out as {'value': 0}. Normal construction fails inside the tool body, which is usually what you want.
Changing L540 to get_type_hints(type_annotation, include_extras=True) fixed the plain class and the dataclass cases locally, with TypedDict unchanged. I have not run the repo's test suite against it.
Activity
dhvani7014 commentedon Oct 15, 2026
Hi, I would like to work on this if it's not already taken.
sattyamjjain commentedon Oct 15, 2026
Looks like the cause is L540 in func_metadata.py at 754254c. The Case 4 path (dataclasses and plain annotated classes) calls
get_type_hints(type_annotation)withoutinclude_extras=True, soAnnotatedis stripped before_create_model_from_classbuilds the model. The TypedDict rebuild at L595 already passesinclude_extras=True.python-sdk/src/mcp/server/mcpserver/utilities/func_metadata.py
Line 540 in 754254c
Dataclasses are affected too. On MCP 2.3.0, pydantic 2.14.1, Python 3.13, a
@dataclasswithvalue: Annotated[int, Field(gt=0)]gives{'title': 'Value', 'type': 'integer'}andconvert_resultaccepts{'value': 0}.Workarounds until it is fixed:
exclusiveMinimum: 0,and{"value": 0}raisesgreater_than.model_construct(value=0)still goes out as{'value': 0}. Normal construction fails inside the tool body, which is usually what you want.Changing L540 to
get_type_hints(type_annotation, include_extras=True)fixed the plain class and the dataclass cases locally, with TypedDict unchanged. I have not run the repo's test suite against it.