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

Goes well beyond the annotations: annotations only say write, non-idempotent, non-destructive, open-world, while the description discloses the full human-in-the-loop flow (a person reviews, replies by email), that no refund is executed automatically, and an explicit security constraint ('never send card numbers'). This is exactly the kind of downstream-behavior disclosure annotations cannot express.

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?

Four short, front-loaded sentences that each carry weight; the request-vs-refund distinction arrives first. Slight redundancy between 'It only files a request' and 'never refunds anything by itself', but the emphasis is defensible for a safety-sensitive operation.

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 4-parameter write tool with no output schema, the description closes the important gaps: it explains what happens after invocation (human review, email reply) and constrains what data the agent may pass. Nothing needed to call it correctly is missing.

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 every parameter is already documented (including the Stripe/order number formats and reason examples). The description only restates the required triple without adding syntax, format, or optionality detail, 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 ('Files a refund request for a past order') and immediately narrows the scope by clarifying it is a request-filing tool, not a refund engine. None of the siblings (checkout, product, shipping, search) overlap, and the description makes the boundary explicit rather than relying on the reader's inference.

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?

Clearly signals the context of use — a past order needing a refund — and that a human reviews and replies by email, which tells the agent to expect a non-instant outcome. It does not name explicit when-not conditions or alternatives, but no sibling competes for this task.

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