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

Annotations declare destructiveHint=true and openWorldHint=true but say nothing about the async contract. The description supplies the critical behavior: it returns a queued operation immediately, is not confirmation of provider completion, an uncertain SMTP attempt is never auto-retried, and progress must be polled via get_mail_action. This is exactly the value-add structured fields cannot carry.

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?

Front-loaded purpose followed by operational rules, all in five tight sentences. The final sentence ("Never retry an uncertain send with a new operationId") restates the earlier retry guidance, a minor redundancy that costs a point.

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?

With no output schema and a complex async send path, the description covers the return contract, polling tool, and retry policy, which is most of what an agent needs. It omits the semantics of replyAll and senderIdentityId, a modest gap for a 7-parameter mutation.

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 only 29% (accountId, senderIdentityId, textBody, htmlBody, replyAll are undocumented in the schema). The description explains operationId semantics well (stable, retry-only reuse) and reinforces messageId handling, but leaves replyAll and senderIdentityId meaning unaddressed, so it only partially compensates.

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?

"Reply to a message" is a specific verb+resource that clearly separates it from send_email, forward_email, and create_draft among the siblings. It does not explicitly name those alternatives, so differentiation relies on the reader's inference.

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?

It gives concrete usage context: supply a stable operationId, reuse it only for retries, and poll get_mail_action. The retry/idempotency guidance is explicit, but it never states when to prefer this over, say, forwarding or starting a new thread.

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