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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, so the mutation profile is covered. The description adds real value beyond them: it counts against a monthly send limit, fails when no recipient is set, and sendAt keeps the draft in Drafts until dispatch. It stops short of stating reversibility, but the destructive annotation carries that.

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, zero filler, and the core action plus its side effect (removal from Drafts) are front-loaded before the conditional sendAt behavior.

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?

No output schema exists, so return values need not be explained; the description covers the mutation, the rate-limit side effect, the failure precondition, and the scheduling variant. Nothing needed to call it correctly 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 description coverage is 100%, so the baseline is 3. The description goes further for sendAt by explaining the behavioral consequence (draft remains in Drafts, sent as it stands then), which the schema does not state, though it adds nothing for uid or mailbox.

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 (send) and resource (draft), plus the crucial scope detail that it sends the draft 'as it stands now (including any edits a person made to it)'. This clearly distinguishes it from update_draft (modify) and send_message (new outgoing mail).

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 clear context for use: it operates on an existing draft, fails if there is no recipient, and with sendAt it schedules rather than sends immediately. It does not explicitly name alternatives such as send_message or update_draft, but the conditions that select this tool are clear.

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