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

Annotations only flag destructive/openWorld/idempotent; the description goes well beyond them by disclosing downstream side effects (operator notified via WhatsApp/email, customer emailed a cancellation notice), the exact idempotency behavior (returns cancelled=true without re-notifying), and the refusal path for operator-confirmed requests.

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 preconditions and 'never call it to test/explore' warning are front-loaded, and every sentence carries operational weight. It is dense and a bit long, but no sentence is filler.

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?

Given an output schema exists, return values need no explanation, and the description still covers side effects, idempotency, refusal cases, and the correct fallback tool. An agent has everything needed to invoke it safely.

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 schema already documents reference, customerEmail, and the optional 200-char reason. The description reinforces that customerEmail must be the address used at submission, but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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+resource (cancels a pending/assigned transfer request) and names the exact prerequisites: the booking reference returned by create_transfer_request plus the submission email. It clearly separates itself from siblings by pointing to create_transfer_request and get_request_status by name.

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 when-to-use (customer asked to cancel and you hold the reference/email), explicit when-not (never to explore or test, not for unsure customers, not for confirmed requests, not for changes or refunds), and names the alternative tool to check state first. Nothing is left to inference.

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