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

Annotations already declare destructiveHint=true and non-idempotent, and the description reinforces the mutation by explaining the draft leaves Drafts (to Sent on Outlook). It adds context annotations cannot carry: attachments are sent as stored and the recipient allowlist constraint. Remaining gaps (failure behavior when the allowlist rejects) are minor.

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 sentence that front-loads the core action and folds side effects and the allowlist constraint into parentheticals — no filler, nothing that fails to earn its place.

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 strong annotation coverage of the safety profile, the description supplies what an agent still needs: attachments included, the draft's removal from Drafts, and the allowlist precondition. It could say more about what happens when the send is refused, but it is largely complete.

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 four parameters are already documented in the schema, including expect_fingerprint's refusal-on-change semantics. The description adds only the indirect point that recipients are not parameters but come from the draft; baseline 3 applies when the schema does the heavy lifting.

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?

The description states a specific verb and resource ('Sends a draft exactly as stored in the Drafts folder') plus scope details (attachments included, leaves Drafts, moves to Sent on Outlook), which clearly separates it from send_message and reply_send without opening any 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?

It gives a real precondition — recipients come from the stored draft and must match send_allowlist — and the schema notes the uid comes from create_draft or a Drafts search, implying this is the follow-up to composing. It never explicitly routes the agent away from send_message/reply_send, so it is clear context rather than full when/when-not guidance.

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