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

With no annotations supplied, the description carries the full behavioral burden and does a fair job: it declares read-only, states the see_prices permission requirement for amounts, and discloses the notable access behavior that payments in non-member shops return not-found rather than an error. It leaves finer details (rate limits, what happens without see_prices) unstated.

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?

Five short sentences, front-loaded with what is returned and followed by identifier, safety, access, and permission caveats. Fragmentary phrasing ("Read only.") is efficient rather than confusing, with no filler.

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?

An output schema exists, so return values need no explanation, and the remaining necessary facts for a one-parameter read tool — identifier origin, read-only nature, access scope, price permission — are all present. Minor gaps around permission-failure behavior keep it short of complete.

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 0% and the single parameter is documented only as a UUID, so the description must compensate. It does, by identifying charge_id as the same identifier that invoices.refund consumes, which is genuine semantic detail an agent could not get from the schema.

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?

"One card or bank payment, with the amount sent back and each refund" names a specific resource and a single-item scope, which implicitly separates it from a list-style sibling. It is clear what the tool retrieves, though it never names the list alternative explicitly.

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 implied by "One ... payment" plus the note that the id is the same charge_id that invoices.refund accepts, which tells an agent where the identifier comes from. There is no explicit when-to-use / when-not-to-use statement or named alternative such as payments_list.

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