Microsoft 365 MCP Server

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

Annotations indicate this is a write operation (destructiveHint=true, readOnlyHint=false). The description adds valuable behavioral context beyond annotations: it explains the two-step workflow (create draft now, send later), details the base64 encoding requirement for MIME format, and notes that drafts can be updated later. No contradiction with annotations.

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?

While information-dense, the formatting is messy with inconsistent bullet points (using dashes without clear line separation) and the final sentence about single-operation replies is awkwardly appended. The content earns its place, but the structure hinders readability.

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?

Given the complex nested input schema (Message object with 20+ properties), the description covers the critical format-specific constraints well. However, no output schema exists, and the description fails to indicate what the tool returns (e.g., the created draft object or ID), which is necessary for a creation tool.

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?

Schema coverage is 75% (baseline 3). The description significantly adds value by clarifying the mutual exclusivity between the Comment and Message body properties, explaining the base64 encoding requirement for MIME format, and detailing the RFC 2822 logic for recipient handling—none of which are inferable from the schema structure alone.

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?

The description clearly states the tool creates a draft reply to a message sender in JSON or MIME format. It mentions the sender specifically, which implicitly distinguishes it from a 'reply-all' operation, though it could explicitly differentiate from siblings like create-reply-all-draft or create-forward-draft.

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 explicit when-not-to-use guidance by mentioning the alternative to 'reply to a message in a single operation' (referring to reply-mail-message). Details specific error conditions (HTTP 400 when both comment and body are specified) and RFC 2822 requirements for replyTo handling, giving clear operational constraints.

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