List refunds

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description adds nothing behavioral beyond that: no mention of the default limit of 10, pagination via cursors, or the shape of the returned list, which is the context a calling agent would actually need.

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 repeats "List refunds" verbatim in back-to-back sentences, wasting the most prominent position on pure duplication. The remaining content is a single useful clause, so the text is short but poorly structured rather than economical.

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 simple, fully optional-parameter list endpoint with complete schema documentation, rich annotations, and no output schema, the definition contains enough to call it correctly. The missing pieces are pagination and default-limit behavior, which are minor for this tool's complexity but would still help an agent.

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 every parameter is already documented, including the `payment` filter, `created` date range, and both cursors. The description's note about `payment` largely restates what the schema says, so it neither compensates for a gap nor adds notable new meaning; the baseline of 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?

The description uses a specific verb plus resource ("List refunds"), which is unambiguous. It does not distinguish this tool from close siblings such as get_refund, get_refund_by_reference, or list_payments, so it stops short of a 5.

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 only usage cue is "Filter by `payment` to see the refunds of one payment," which implies when the filter is appropriate. There is no guidance on when to use this instead of get_refund for a single refund, or how it relates to list_payments.

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