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

Beyond the annotations (which already say idempotent, non-destructive, mutating), the description explains the consequence of each reason: faulty/not_as_described/wrong_item fall under a legal guarantee at no cost to the customer, while changed_mind is a withdrawal within the period or a business-policy return after it. It also states the return is created as a linked object visible under refunds in get_item_status, filling in for the missing output schema.

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?

Front-loads the precondition, then reason semantics, then lines, then outcome; each clause carries information and there is no redundancy. The telegraphic style is dense but readable.

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 9-parameter mutation with no output schema, the description covers trigger, reason consequences, line selection, and the observable result (a linked return listed under refunds). It omits what happens next in the lifecycle (approval, who accepts) but is sufficient to invoke correctly.

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 78% and already documents key, pass, idempotency_key, and lines. The description adds real meaning for reason by explaining the legal and cost implications of each enum value, and clarifies lines semantics (indices into orderedItem, omitted means all), which is more than a restatement.

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 (ask to send goods back) and resource (goods from an order), with a clear precondition: it applies once the goods reached the person. An agent can distinguish it from cancel_item or withdraw_from_contract by that precondition alone.

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 a concrete activation condition ('once an order's goods reached your person') and explains which reason values are available and their legal consequences, which guides selection. It does not explicitly exclude or name alternatives for cases like unshipped orders, leaving a small gap.

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