[Anish Mehta (anishmehta24)]

Motivation & Context

_get_input_model_from_mcp_prompt builds the argument schema with prompt_argument.description if hasattr(prompt_argument, "description") else "". PromptArgument always has the attribute (it's an optional pydantic field), so an argument without a description comes through as None:

p = types.Prompt(name="p", arguments=[types.PromptArgument(name="topic", required=True)])
_get_input_model_from_mcp_prompt(p)
# {'type': 'object', 'properties': {'topic': {'type': 'string', 'description': None}}, 'required': ['topic']}

description has to be a string in JSON Schema, so a provider that validates tool schemas strictly can reject the tool.

Description & Review Guide

• What are the major changes? Add description only when the argument has one.
• What is the impact of these changes? MCP prompts whose arguments have no description produce a valid schema.
• What do you want reviewers to focus on? Leaving the key out rather than using "", since an empty description adds nothing.

Related Issue

No existing issue.

Contribution Checklist

• The code builds clean without any errors or warnings
• All unit tests pass, and I have added new tests where possible

Test: test_get_input_model_from_mcp_prompt_argument_without_description in tests/core/test_mcp.py; it fails on main. pytest packages/core/tests/core/test_mcp.py passes, and ruff and the repo's pre-commit checks are clean.

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

[Eduard van Valkenburg (eavanvalkenburg)]

Anish Mehta (@anishmehta24) Reviewed the current head and found no blocking issues.