Send the reviewed saved draft

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

Annotations already declare destructiveHint=true and idempotentHint=false, yet the description adds genuinely new behavior: revision-guard refusal, request_key-based idempotency across interruptions, and the ambiguity of an unknown outcome. The `confirm` flag's role in the send path is left unexplained, which keeps it from a 5.

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?

Four short sentences, each carrying a distinct operational rule, front-loaded with the primary action before the refusal and retry caveats. No filler.

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?

Output schema exists so return values need not be described, and the destructive/idempotency profile is well covered. However, a destructive tool with five undocumented parameters leaves the `confirm` gate ambiguous, which is a real completeness gap for safe invocation.

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 0%, so the description must carry all parameter meaning. It covers mode and request_key well and implies expected_revision via the "changed draft is refused" rule, but draft_ref and especially the `confirm` boolean are never explained despite gating a destructive send.

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 ("Send exactly the saved draft revision the user reviewed, or queue it"), making the send/queue duality clear. It implicitly separates itself from mail_send and mail_draft_save by binding to a saved, reviewed revision, but never names those siblings explicitly.

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-not conditions ("A changed or open draft is refused"), explicit retry policy (reuse request_key after interruption; never retry with a new key when the result is unknown), and clarifies mode=later's effect. These are exactly the decision rules an agent needs before invoking a destructive operation.

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