Support index descriptions end-to-end

[sudhz]

Purpose

This PR adds comprehensive support for index descriptions in the Azure AI Search MCP server. Previously, index descriptions were not accessible through the MCP tools, making it difficult for users to understand the purpose and content of different search indexes.

Changes

• Added new list_indexes_with_descriptions tool that retrieves both names and descriptions of all search indexes
• Updated data models to include description field support
• Enhanced DAO layer to handle description retrieval
• Updated API version to 2025-05-01-preview to leverage latest Azure AI Search features
• Added comprehensive unit tests for the new functionality
• Updated documentation to reflect the new capability

Does this introduce a breaking change?

[ ] Yes
[x] No

Pull Request Type

[ ] Bugfix
[x] Feature
[ ] Code style update (formatting, local variables)
[ ] Refactoring (no functional changes, no api changes)
[ ] Documentation content changes
[ ] Other... Please describe:

How to Test

1. Get the code:

git clone https://github.com/sudhz/mcp-foundry.git
cd mcp-foundry
git checkout main

2. Set up your environment with Azure AI Search credentials
3. Run the new tool:

from mcp_foundry.mcp_foundry_knowledge.tools import list_indexes_with_descriptions
result = await list_indexes_with_descriptions()

4. Run tests:

pytest tests/test_knowledge_dao.py -v

What to Check

• New tool returns both index names and descriptions
• Handles cases where description is None gracefully
• Backward compatibility with existing tools is maintained
• Unit tests pass

[sudhz]

Hi maintainers, could you please review and help approve this PR? Thanks!

@tendau @Tanvi26Kori @izzymsft @luigiw @dennisfeng20 @amynic @sesispla @Hitesh95 @Rsirp0c @farzad528 @dem108 @kdestin