Draft a reply

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

With only generic annotations (readOnly=false, destructive=false), the description carries useful weight: it discloses the header construction, subject rewriting, body quoting, and the non-sending guarantee. It does not say which folder the draft lands in or what happens on repeated calls (annotations mark it non-idempotent), leaving a small gap.

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?

Three tight clauses, no filler, and the non-sending constraint plus the return-value handoff are front-loaded rather than buried.

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 an 8-param mutation tool with no output schema, the description covers the two things an agent most needs: the side effects it produces and that it returns a draft UID for send_draft. Nothing critical about invocation is missing.

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 63%, and the description fills the most important hole by explaining the two undocumented behavior-bearing flags: replyAll (copies other To/Cc) and quoteOriginal (original quoted below). cc/bcc/account/folder remain schema-only, which is acceptable for self-evident fields.

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?

Opens with a specific verb+resource ("Save a reply to a message as a draft") and immediately enumerates the concrete effects (In-Reply-To/References, "Re:" subject, quoted original). This clearly separates it from create_draft (new message) and send_draft (sends), which is exactly the distinction an agent needs.

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?

"Does NOT send; returns the draft UID for send_draft" tells the agent this is step one of a two-step flow and names the follow-up sibling. It implies the reply-vs-new-draft split but never states it explicitly or describes when replyAll should be preferred.

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