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

Annotations only declare write/idempotent/non-destructive; the description goes far beyond by disclosing the approval workflow, the 'To send' holding state, the contact_suppressed refusal condition, and the warning code vocabulary. It also names the required draft_email scope, which annotations cannot express.

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 core action and the approval consequence are front-loaded, and nearly every sentence carries non-obvious operational detail. It is a single dense paragraph though, with warning-code enumeration mid-stream that could be structured for faster scanning.

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, the description compensates by naming the response fields (warnings codes, prior_emails) and explaining what each signals. Combined with refusal conditions, scope requirements, and argument rejection behavior, an agent has everything needed to call this correctly and interpret the result.

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 coverage is 100%, so the baseline is 3, and the description adds real semantics: contact_id and to are alternatives, one recipient only, plain-text body with platform-added footer. It loses a point because its 'accepts only contact_id (or to), subject, body' enumeration omits idempotency_key, which the schema documents and the annotations advertise as idempotent — a minor inconsistency an agent could trip over.

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 opening sentence states a specific verb and resource ('Draft one email to a contact') and immediately bounds scope: one recipient, plain text, no attachments. No sibling in the list (add_note, list_email_status, campaign tools) could be confused with this operation.

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 concrete usage context: drafts are auto-approved unless the operator enabled approval, and 'check them before drafting a second message to the same person' is an explicit precondition. It never names an alternative tool or an explicit case where you should not draft at all, so it stops short of 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.