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

With no annotations provided, the description carries the full burden of behavioral disclosure. It goes beyond a simple 'refunds an order' by explaining that refunding revokes the entitlement, invalidates new download tokens, and that local copies remain with the buyer. This is rich, honest transparency about side effects.

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 concise and well-structured. It front-loads the core purpose, then uses a numbered list for the policy, and a separate sentence for consequences. Every sentence provides necessary information without waste.

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 the tool's complexity and lack of annotations or output schema, the description covers the essential aspects: what it does, eligibility, and consequences. It does not explain the success/failure response format, but that is not required by the schema and the policy detail makes the tool usable.

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?

The input schema has 100% coverage for both parameters: order_id describes its source (purchase_book or my_orders), and reason is clearly logged but not user-facing. The description adds no additional parameter-specific meaning, warranting the baseline score of 3.

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 'Request a refund for a previous order,' which is a specific verb+resource statement. It clearly identifies the action and object, and the detailed refund policy further distinguishes it from sibling tools like purchase_book and my_orders.

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 explicit eligibility criteria via the refund policy (within 7 days, no annotation, download count, refund count), which tells the agent when the tool is applicable. It does not explicitly mention alternatives, but the policy acts as clear when/when-not guidance.

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