Send approved email draft

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

Annotations already indicate this is a non-read-only, idempotent, non-destructive operation. The description adds useful behavioral context beyond those annotations: it requires a fresh stable idempotency key and warns that SMTP acceptance is reported separately from final delivery. It does not fully describe failure behavior, but it provides meaningful operational transparency.

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?

The description is two sentences with no filler. The critical precondition ('only after the user explicitly approves the exact current preview') is front-loaded, followed by required inputs and an important caveat. Every sentence carries essential information.

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?

For a sensitive send operation with no output schema, the description covers the key prerequisite, required tokens, idempotency, and the SMTP/delivery distinction. It does not describe the response shape or error cases, but the existing guidance is enough for an agent to invoke the tool correctly in the intended approval workflow.

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 compensate. It clarifies that revision and confirmationToken are tied to the approved preview, that idempotencyKey should be new and stable, and that the confirmed flag corresponds to explicit user approval. DraftId is left implicit as a resource identifier, but overall the description adds substantial meaning beyond the raw 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?

The description clearly states the tool sends an approved email draft, using the specific verb 'send' and resource 'approved email draft.' It also distinguishes this action from other draft operations by requiring explicit user approval of the current preview, so an agent can tell it apart from preview, update, or discard tools.

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?

The description gives a strong precondition: only use after the user explicitly approves the exact current preview. It also implies the necessary confirmation flow by mentioning revision, confirmation token, and idempotency key. However, it does not explicitly name sibling alternatives or state when not to use this tool in favor of another.

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