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

Annotations only supply destructiveHint=true; the description carries far more: cap accounting, refusal error shape { error, code: send_blocked, reason, retryable }, retryability rules, idempotency collapse with a 10-minute body-hash fallback window, deduplicated semantics, and the 404 no-mailbox case. Nothing contradicts the destructive hint and it richly extends it.

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?

One dense paragraph, but front-loaded with purpose then inline 'Inputs:'/'Returns:' structure, and every sentence carries operational value (refusal codes, idempotency). Slightly heavy for a 3-param tool, but no filler to cut.

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?

There is no output schema, so the description correctly spells out return values ({ messageId, deduplicated }, the error envelope), plus the 404 case. For a side-effecting send tool, an agent has everything needed to call, retry, and interpret results.

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 67%, and the description adds real meaning the schema lacks: the idempotencyKey's purpose, the body-hash fallback matched only 10 minutes, and how to force a genuine resend ('pass a key, or vary the body'). threadId/body are named but not elaborated beyond the schema.

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 ('Send a reply on an existing thread, from the mailbox that sent it'), which is unambiguous and distinct from siblings like launch_campaign (new sends) or inbox/thread (reads). An agent can select it without opening the schema.

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?

Gives explicit when-and-when-not guidance: it is 'governed like campaign sends,' REFUSED rather than silently dropped on suppression/pause/cap, retryable only for cap and cleared at daily rollover, and explicitly warns 'stop retrying, do not loop replies to manufacture volume.' This is unusually actionable routing/retry guidance.

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