create-reply-draft

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

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the write nature is known. The description adds behavioral details: creates a draft (not sending), constraints on parameters, MIME encoding requirements, and tips about HTML and signatures. No contradictions 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?

The description is well-structured with separate paragraphs for JSON and MIME formats, plus a tip section. Every sentence adds value, though it is slightly verbose. The key purpose is front-loaded.

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?

While the description covers core usage and constraints, it lacks information about required permissions, the response format (no output schema), and error handling. It mentions updating the draft later but doesn't specify the return type or confirmation feedback.

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?

The description adds significant meaning beyond the schema: explains the body parameter's two formats with constraints, and provides clear guidance for messageId (pass under 'messageId', not 'id'). Schema coverage is 80%, but the description fills gaps like MIME format instructions and the comment vs body restriction.

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 to reply to the sender, specifying JSON or MIME format. This distinguishes it from sibling tools like create-forward-draft and create-reply-all-draft. The verb 'create' and resource 'draft to reply to sender' are specific.

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 provides clear context on when to use JSON vs MIME format and highlights constraints (e.g., cannot specify both comment and body). It mentions an alternative: replying in a single operation with reply-mail-message. However, it does not explicitly compare with create-forward-draft or create-reply-all-draft.

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