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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is fully covered. The description adds no behavior beyond restating the endpoint: nothing about pagination behavior, empty results, or result ordering. With annotations doing all the work, this contributes little.

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?

Two terse sentences with the scope stated first; nothing is padded. The raw endpoint path is somewhat redundant given the title and name already convey the operation, but it's compact and front-loaded.

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 two-parameter read-only list, the description plus a fully documented schema is nearly sufficient. However, it says nothing about what a refund record contains or pagination flow (the schema covers paging but the description doesn't reinforce it), leaving a modest gap.

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% — charge_token format (ch_...) and the page parameter with its 25-per-page and next_page guidance are both documented in the schema. The description adds no parameter meaning beyond that, so 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?

States a specific resource (refunds) with a precise scope (refunds issued against a single charge), plus the underlying endpoint GET /charges/{token}/refunds. It implicitly distinguishes itself from the sibling pinpayments_list_refunds (all refunds) and pinpayments_get_refund (single refund), though it never names either alternative.

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?

Usage is only implied: the phrase 'issued against one charge' tells an agent this is the scoped variant of listing refunds, but there is no explicit when-to-use, when-not, or pointer to pinpayments_list_refunds for cross-charge queries.

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