Python: Return MCP tool-use sampling results

[scarab-systems]

Motivation & Context

MCP sampling requests can forward tool schemas to the configured chat client, but structured responses that come back as Agent Framework function-call content were not converted back to MCP tool-use content. This caused structured sampling clients to receive an internal error instead of the tool-use result.

Fixes #7160

Description & Review Guide

• What are the major changes?

  • Convert Agent Framework function_call content into MCP ToolUseContent.
  • Return CreateMessageResultWithTools with stopReason="toolUse" when sampling produces tool-use content.
  • Collect prepared content across all response messages so multiple function calls are preserved.
  • Add regression coverage for structured sampling output with multiple tool-use calls.

• What is the impact of these changes?

  • Structured MCP sampling can return tool-use results while existing text/image sampling behavior is preserved.
  • The change is additive to the sampling response path and does not remove existing fallback/error handling.

• What do you want reviewers to focus on?

  • The function-call to ToolUseContent mapping and the precedence of structured tool-use responses over plain text/image selection.

Related Issue

Fixes #7160

Contribution Checklist

• The code builds clean without any errors or warnings
• All unit tests pass, and I have added new tests where possible
• The PR follows the Contribution Guidelines
• This PR is linked to an issue and there is no other open PR for this issue (see Related Issue above).
• This is not a breaking change. If it is a breaking change, add the breaking change label (or add "[BREAKING]" to the title prefix, before or after any language prefix) — a workflow keeps the label and title prefix in sync automatically.

[Copilot]

Pull request overview

This PR fixes Python MCP sampling so that structured model outputs returned as Agent Framework function_call content are converted back into MCP ToolUseContent, allowing structured sampling clients to receive tool-use results instead of an internal error.

Changes:

• Add Agent Framework function_call → MCP ToolUseContent conversion in _prepare_content_for_mcp().
• Update sampling_callback() to aggregate content across all response messages and return CreateMessageResultWithTools(stopReason="toolUse") when tool-use content is present.
• Add a regression test covering multiple tool-use calls returned from a sampling response.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.

File	Description
python/packages/core/agent_framework/_mcp.py	Converts function_call content into MCP ToolUseContent and returns CreateMessageResultWithTools when tool-use content is produced during sampling.
python/packages/core/tests/core/test_mcp.py	Adds regression coverage ensuring multiple function calls are preserved and returned as MCP tool-use sampling results.