Draft a reply

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

Annotations already declare non-read-only, non-destructive, non-idempotent and open-world, and the description adds meaningful behavior beyond them: automatic subject prefixing, quoting of the original, and reply headers. 'Nothing is sent' is a genuinely useful reassurance for an agent wary of firing off mail.

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?

A single sentence with the action front-loaded and a parenthetical enumerating the exact side effects. No filler and nothing an agent must read past to find the core behavior.

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 write tool with no output schema, it covers what is created and that nothing is transmitted, but is silent on the consequence of the non-idempotent hint (calling twice produces two drafts) and on failure modes for an invalid message id. These are the details an agent most needs when deciding whether a retry is safe.

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 description coverage is 100%, so all five parameters are already documented, including the quoting note on body and the folder enumeration. The description adds no parameter-level guidance beyond what the schema provides; baseline 3 applies.

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?

States a specific verb and resource (writes a reply, saves it to Drafts) and adds the distinguishing detail that the result is threaded. It doesn't explicitly contrast with the sibling create_draft, but 'reply to a message' is concrete enough that an agent can tell the two apart.

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?

Usage is only implied by 'reply to a message'; there is no statement of when to prefer this over create_draft, or what to do if the referenced message is not replyable. The 'Nothing is sent' clause hints at a follow-up send step but doesn't name or route to it.

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