Microsoft 365 MCP Server

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

Beyond the destructiveHint annotation indicating mutation, the description adds valuable behavioral context: it discloses HTTP 400 error conditions, RFC 2822 compliance requirements for replyTo handling, the ability to update the draft later, and that sending requires a subsequent operation. This helps the agent understand the draft lifecycle and constraint violations.

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?

The content is information-dense and necessary for the tool's complexity, but the structure suffers from informal dash-bullet formatting and a grammatically incomplete final sentence fragment ('Alternatively, reply-all to a message in a single action.'). The JSON vs MIME instructions could be more clearly delineated.

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?

For a complex dual-format operation with nested object parameters, the description adequately covers input constraints and draft lifecycle. However, lacking an output schema, it should briefly mention what the tool returns (e.g., the created draft object) to be complete. It does not address the 'includeHeaders' or 'excludeResponse' parameters visible in the schema.

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?

While the schema has 75% coverage, the description adds critical semantic constraints not captured in the schema structure—specifically the mutual exclusivity rule between 'comment' and 'body' properties within the message parameter, and the base64 encoding requirement for MIME content. This prevents invalid invocations that the schema alone would allow.

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?

Clearly states the specific action (create draft), scope (reply-all to sender and recipients), and supported formats (JSON/MIME). The phrase 'reply to the sender and all recipients' effectively distinguishes this from the sibling 'create-reply-draft' tool which targets only the sender.

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 detailed format-specific constraints (e.g., mutual exclusivity of 'comment' vs 'body' properties causing HTTP 400 errors). Mentions 'Alternatively, reply-all to a message in a single action,' implicitly referencing the sibling 'reply-all-mail-message' tool as an alternative, though it could be more explicit about when to choose between creating a draft versus sending immediately.

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