create-reply-draft

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

The description goes well beyond the annotations (readOnlyHint: false, destructiveHint: true) by detailing key behaviors: the 400 error when both comment and body are supplied, the note that supplying body replaces the entire draft body so quoted history is lost, the MIME base64 requirement, and that signatures are only added by the Outlook client, not via Graph. These are valuable, non-obvious details that help an agent predict behavior accurately.

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 description is relatively long but well-structured with bullet points and clear formatting. It leads with the primary purpose, then details each format, and provides a tip and note. Despite its length, every sentence conveys necessary information; it is appropriately detailed for a complex tool with two distinct input formats.

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 tool with two complex input formats, nested schemas, and error-prone conditions, the description is extremely complete. It covers format selection, header requirements, attachments, error cases, update workflow, and the alternative single-operation reply. No output schema is needed, and the description leaves no obvious gaps for an agent to call this tool correctly.

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 schema coverage is high (80%), the description adds meaningful semantics for the body parameter (explaining the Comment vs Message distinction and the error condition) and for messageId (instructing to pass it as 'messageId' not 'id'). It also clarifies that attachments and S/MIME properties go into the MIME content. This adds value beyond the schema's basic property descriptions.

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's purpose: 'Create a draft to reply to the sender of a message in either JSON or MIME format.' It specifies the verb, resource, and formats, and distinguishes itself from siblings like create-forward-draft and create-reply-all-draft by its focus on replying to the sender only. The mention of 'Alternatively, reply to a message in a single operation' further clarifies its scope.

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?

The description implies when to use this tool: when you want to create a draft rather than send immediately ('Send the draft message in a subsequent operation'), and it mentions the alternative of replying in a single operation. However, it does not explicitly name any sibling tools (e.g., create-reply-all-draft, reply-mail-message) or provide clear exclusions, so the guidance is implied but not explicit.

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