Open
Description
Describe the bug
The documentation for creating custom FunctionTool objects directly (without using the @function_tool decorator) shows an example that fails with OpenAI's Responses API due to missing additionalProperties: false in the JSON schema.
The example from the docs:
tool = FunctionTool(
name="process_user",
description="Processes extracted user data",
params_json_schema=FunctionArgs.model_json_schema(), # This line is the problem
on_invoke_tool=run_function,
)This results in the error:
Error code: 400 - {'error': {'message': "Invalid schema for function 'process_user': In context=(), 'additionalProperties' is required to be supplied and to be false.", 'type': 'invalid_request_error', 'param': 'tools[0].parameters', 'code': 'invalid_function_parameters'}}
Debug information
- Agents SDK version: 0.1.0
- Python version: 3.10.16
Repro steps
from typing import Any
from pydantic import BaseModel
from agents import RunContextWrapper, FunctionTool, Agent, Runner
class FunctionArgs(BaseModel):
username: str
age: int
async def run_function(ctx: RunContextWrapper[Any], args: str) -> str:
parsed = FunctionArgs.model_validate_json(args)
return f"{parsed.username} is {parsed.age} years old"
# This fails with OpenAI 400 error
tool = FunctionTool(
name="process_user",
description="Processes extracted user data",
params_json_schema=FunctionArgs.model_json_schema(),
on_invoke_tool=run_function,
)
agent = Agent(
name="Test Agent",
instructions="You are a test agent",
tools=[tool]
)
# This will fail when the agent tries to use the tool
result = Runner.run_sync(agent, "Process user data for John who is 30 years old")Working fix (not documented):
from agents.strict_schema import ensure_strict_json_schema
tool = FunctionTool(
name="process_user",
description="Processes extracted user data",
params_json_schema=ensure_strict_json_schema(FunctionArgs.model_json_schema()), # Fix
on_invoke_tool=run_function,
)Expected behavior
Either:
- The documentation example should work as-is, OR
- The documentation should clearly show that
ensure_strict_json_schema()must be called on Pydantic schemas when creatingFunctionToolobjects directly, OR - The
FunctionToolconstructor should automatically apply strict schema validation whenstrict_json_schema=True(which is the default)
The current behavior is inconsistent - the @function_tool decorator automatically applies strict schema validation, but the FunctionTool class does not, despite both having strict_json_schema=True by default.