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

Annotations declare destructiveHint=true and idempotentHint=true, and the description adds substantial context beyond them: nothing is transmitted until confirm_withdrawal is sent, the first call returns a statement (confirm.statement), refunds differ depending on whether goods shipped, only specified lines come back, and the business emails a copy. It also discloses the non-returnable / passed_on escalation path, which no structured field covers.

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?

Every sentence carries real information and the purpose is front-loaded, but the prose is a dense run-on with awkward phrasing ('withdrawal on get_item_status', 'passed_on') that makes it harder to parse than the content warrants.

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 still conveys the two-step protocol, the statement response, and the refund/return outcomes, and the schema documents the eight parameters well. It stops short of describing the shape of the returned statement or the exact fields sent to the business, which an agent executing the flow would want.

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 already 88%, so the schema carries most parameter meaning. The description does add a conditional rule for 'lines' (only used once goods reached the person) and links confirm_withdrawal to the person's confirmation, but adds little about item_id, pass, key, or idempotency_key beyond what the schema states.

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 and resource — a person withdrawing from a paid booking or order within the business's stated withdrawal period — and contrasts it with a return handled under the business's own policy. It is clearly distinguishable from a generic cancellation, though it never names the sibling cancel_item or request_return tools directly.

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?

Gives explicit scope conditions: use only within the period the business states, obtained via get_item_status, and never for expired, non-returnable, or passed_on cases. The two-step confirm flow and the refund/return branches are spelled out, but the alternatives for the excluded cases are described as concepts rather than by tool name (e.g. request_return).

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