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

Annotations only say readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the description must explain the actual side effects — and it does: no email is sent, a plan credit is consumed, and Pro tier is required. Where it falls short is persistence: it never says whether the generated draft is stored server-side, which matters given readOnlyHint=false and is a plausible point of confusion with 'nothing is sent'.

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?

Three short sentences, each earning its place: what it does and in what language, what happens next, and what it costs. The alternative tool and the safety fact ('nothing is sent') appear before the billing details, so the agent sees the critical routing information first.

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 2-parameter generation tool with no output schema, the description covers input shape, language behavior, follow-up action, and quota requirements. The only gap is the shape of the returned draft (raw text vs. persisted object with an id usable by reply_to_email), which an agent would need when chaining.

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 baseline is 3; the description earns above baseline by illustrating the 'note' parameter with a realistic example ('refund approved, 20 EUR, in 5 days') and by stating that output language follows the customer rather than the note. thread_id semantics are fully covered by its schema description pointing to list_emails.

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?

Names a specific verb+resource ('Turn a short note ... into a full reply to an email conversation') and adds two distinguishing constraints: it works from an email thread and writes in the customer's language. This clearly separates it from reply_to_email (which sends) and reply_to_ticket (which targets tickets), so an agent can pick correctly without opening schemas.

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?

Explicitly states the two-step workflow — 'Nothing is sent: show the draft, then send it with reply_to_email' — naming the follow-up sibling. It also gives a concrete note example and states the prerequisites ('Spends one AI reply of the plan. Needs Pro or higher'), removing ambiguity about cost and eligibility before calling.

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