Summary

This PR allows you to use the pydanticField decorator to constrain tool arguments for tools decorated with@function_tool (more specifically, for tools usingfunction_schema to parse tool arguments). Such constrains include, e.g. limiting integers to a certain range, but in principle, this should work forany constrains supported by the API.

Specifically, it enables the following syntax:

@function_tooldefmy_tool(age:int=Field(...,gt=0))->str:    ...

Previously, one had to create a nested pydanticBaseModel to achieve this functionality.
Issue#1123 explains this feature request and the previous workaround.

Example:

importjsonfrompydanticimportFieldfromagentsimportfunction_tool@function_tooldefmy_tool(age:int=Field(...,gt=0))->str:returnf"The age is{age}"print(json.dumps(my_tool.params_json_schema,indent=2))

Output: (compare to#1123)

{  "properties": {    "age": {      "exclusiveMinimum": 0,      "title": "Age",      "type": "integer"    }  },  "required": [    "age"  ],  "title": "my_tool_args",  "type": "object",  "additionalProperties": false}

Test plan

I added unit tests intests/test_function_schema.py.

Issue number

Closes#1123.

Checks

• I've added new tests (if relevant)
• I've added/updated the relevant documentation
• I've runmake lint andmake format
• I've made sure tests pass

Note: I am happy to add documentation for this; please point me to where I should do so:)