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

Annotations give destructiveHint=true, already signalling an irreversible mutation. The description usefully reinforces that money moves back and that partial refunds are possible, but adds nothing about idempotency, refund limits, or reversibility beyond what the hint implies.

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?

A single front-loaded sentence with the key effect (money back) stated first, followed by full/partial scope and endpoint. Slightly shouty capitalization but no wasted verbiage.

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 and full schema coverage the description needn't explain returns, but for a destructive money-moving tool with minimal annotations it could say more about idempotency importance or refund constraints. Adequate but with clear gaps.

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 100%, so all five parameters (id, amount in minor units with default, metadata, reference, idempotency_key) are already documented. The description adds no parameter detail beyond the schema, 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?

Names a specific verb (refunds) and resource (a captured payment) plus the money-movement effect and the underlying endpoint. This distinguishes it from siblings like checkout_void_payment and checkout_capture_payment without opening the schema.

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 implies usage (refund a captured payment, full or partial) and states the endpoint, but gives no explicit when-to-use vs. checkout_void_payment or checkout_capture_payment, and no prerequisites such as needing a captured (not merely authorized) payment.

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