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

Adds substantial context beyond the annotations: a 10-minute dedup window, idempotency_key control, dry_run not billing but still counting toward rate limits, and the pending_approval/approval_url outcome. That last point is the kind of non-obvious side effect annotations never express. It stops short of stating auth/permission requirements or delivery failure behavior for the normal path.

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?

Dense but zero-waste: each sentence carries a distinct decision (body source, dry run, dedup behavior, return value, approval fallback). The core action and precondition are front-loaded before the edge-case handling.

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 21-parameter mutation with no output schema, it covers the highest-risk behaviors (dedup, dry run, approvals) and states the return fields (message_id, status). Attachments and scheduling — both with non-trivial mechanics — are only handled by the schema, so the description is strong but not exhaustive.

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?

With 21 parameters at 62% schema coverage, the description usefully explains the body/template tradeoff, the idempotency_key vs allow_duplicate distinction, and that 'from' must be on a verified domain in the key's scope. It says nothing about cc/bcc, attachments, scheduled_at, track_opens/track_clicks, or message_stream, leaving those entirely to the schema descriptions.

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 and resource plus a hard precondition: 'Send one email from an address on a verified domain (see list_domains).' The word 'one' implicitly separates it from send_batch, and the verified-domain constraint plus cross-reference to list_domains gives an agent enough to pick correctly.

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?

Explicit routing rules throughout: give html_body/text_body OR template_alias+template_model; use dry_run: true 'to validate a new or uncertain send without delivering it'; use allow_duplicate for intentional resends. It also tells the agent what to do when human approval is needed (share approval_url), which is a real operational decision point.

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