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

Annotations already provide idempotentHint and safety hints, but the description goes well beyond them by detailing the 30-day change-of-mind window, free returns, full refund, seller-funded label, defective handling under CRA 2015, auto-refund if label is late, and idempotency. No conflicts with annotations.

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 description is dense but every sentence carries essential information: the action, the policy terms, the reason semantics, the defective escalation path, the seller label obligation, and idempotency. It is front-loaded with the core purpose and contains no 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?

The description covers policy, reason behavior, and post-initiation seller obligations well. Since there is no output schema, it does not state the response shape or that a return ID is generated, but this is not critical for invoking the tool correctly given the rich context already provided.

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, but the description adds significant meaning to the reason enum by explaining cooling_off_statutory, cooling_off_extended, and defective with time windows and consequences. It does not add much for order_id or description, but the reason semantics are substantially enriched.

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 description opens with a specific verb and resource: 'Initiate a return on a delivered order.' This clearly distinguishes the tool from sibling tools like returns_get, returns_list, and seller_accept_return by its action of initiating rather than querying or responding.

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 provides clear context on when to initiate a return and which reason codes apply in what timeframes. It does not explicitly name alternative tools or state when not to use this one, but the policy detail about defective items after 30 days gives practical routing guidance.

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