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

The destructiveHint annotation already flags this as a destructive operation, and the description earns credit by spelling out the concrete consequence: it moves real money back to the customer. That goes beyond the annotation's abstraction. It still omits whether the operation is reversible or idempotent, what auth/permissions are needed, and whether benefit revocation is permanent, so it is not full marks.

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 short sentences, front-loaded with the action and scope, then the risk warning, then the endpoint. No filler or redundancy.

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 destructive financial mutation with no output schema, the description covers the action, scope and monetary impact but says nothing about what is returned, whether a refund can be reversed or re-issued, or any idempotency behavior. Adequate against a fully documented schema and a destructiveHint annotation, but not complete for the operation's risk profile.

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 amount, reason, comment, order_id and revoke_benefits are all documented in the schema itself, including the enum and defaults. The description's only parameter-relevant contribution is 'in full or in part', which duplicates the schema's 'Omit to refund the full order'. Baseline 3 is correct.

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?

'Refund an order, in full or in part' gives a specific verb and resource plus a scope qualifier, and no sibling tool performs refunds, so it is easy to distinguish from the surrounding list/get/cancel tools. It stops short of naming an alternative or contrasting with, say, cancel_subscription, so it is clear but not sibling-differentiating.

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?

There is no statement of when to reach for this tool versus alternatives (e.g., cancel_subscription, list_refunds) or any prerequisite such as having an existing order or the appropriate API scope. The only adjacent guidance is a warning about money moving, which is behavioral rather than usage-routing.

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