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

Annotations only declare destructiveHint=true and a title; the description adds genuinely useful context beyond that, making explicit that this MOVES MONEY BACK to the customer and supports both full and partial refunds. It does not cover auth requirements, reversibility, error modes, or the returned refund object, so it stops short of a 5.

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 carrying the verb, the scope, and the financial consequence, followed by the endpoint. Emphasis via capitalization is used sparingly and no sentence is wasted.

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, the description never says what a refund call returns (refund id, status) or how partial-refund totals behave across multiple calls, and it gives no idempotency/permission guidance. The 100%-covered input schema and destructiveHint annotation carry most of the load, so this is adequate but with a notable gap for a money-moving mutation.

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 the schema already documents id, amount (minor units, defaults to full captured amount), metadata, reference, and idempotency_key. The description's 'full or partial' adds a sliver of meaning about amount behavior but largely restates what the amount property already says — baseline 3 is appropriate.

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 (refund a captured payment) with the exact API operation (POST /payments/{id}/refunds), and the word 'captured' implicitly scopes it away from void_payment (uncaptured) and capture_payment. An agent can tell it apart from its siblings without opening a 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?

Usage is implied by 'refunds a captured payment' — the agent can infer this applies to already-captured payments — but there is no explicit guidance on when to choose this over checkout_void_payment or checkout_capture_payment, nor any stated prerequisites (e.g., the payment must be in a refundable state).

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