Microsoft 365 MCP Server

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Strong. Adds critical behavioral details beyond annotations: HTTP 400 error conditions for parameter conflicts, lifecycle notes (can update draft later, send subsequently), and MIME encoding requirements (base64). destructiveHint=true is complemented by 'does not send' clarification. Minor gap: doesn't detail side effects on failure or specific storage location.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Information-dense but slightly verbose. Bullet points effectively organize JSON vs MIME requirements. The 💡 TIP at end repeats the 'does not send' concept mentioned earlier. Front-loading is good (purpose first), but API-level error documentation (HTTP 400 specifics) could be more concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Comprehensive for a complex 4-parameter tool with nested objects. Covers both invocation formats (JSON/MIME), validation rules, lifecycle (create → update → send), and alternatives. No output schema exists, and description appropriately doesn't attempt to document return values per scoring rules.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Highly valuable additions. With 75% schema coverage, description compensates for complex 'body' parameter by documenting mutual exclusivity rules (comment vs body, toRecipients param vs property) that schema cannot express, plus MIME-specific encoding instructions. Schema covers basic types; description covers constraint semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Excellent. Opens with specific verb (Create), resource (draft to forward existing message), and format options (JSON/MIME). Explicitly distinguishes from sibling 'forward-mail-message' by noting single-operation forwarding as an alternative, and distinguishes from reply drafts by specifying 'forward'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear usage context: bullet points detail JSON vs MIME selection criteria, validation constraints (HTTP 400 triggers), and the TIP explicitly states 'Useful when user wants to review before sending.' Mentions single-operation alternative. Minor gap: could explicitly name the sibling tool (forward-mail-message) for clarity.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.