Retrieve a refund by its reference

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

Annotations already cover read-only, idempotent, non-destructive behavior, so the bar is lower; the description still adds value by stating that unknown references return `404 resource_missing` and that refunds created without a reference receive a generated one, which is exactly the kind of response-semantics detail annotations cannot carry.

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 lead sentence is front-loaded and the follow-up sentences each add a distinct fact (uniqueness, auto-generation, 404). The first sentence largely restates the title, a minor redundancy, but nothing else 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?

For a one-parameter lookup with no output schema, the description covers what is looked up, what an unknown reference yields, and how references originate. The only missing piece is how this differs from `get_refund`, which would make the routing decision unambiguous.

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% and the single parameter is documented, so the baseline is 3. The description goes beyond the schema by explaining that references are unique per mode and are auto-generated when omitted, which clarifies what a valid reference actually is.

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 gives a specific verb and resource ('Retrieve a refund by its `reference`'), which is more precise than the bare tool name. It does not, however, explicitly contrast with the sibling `get_refund`, so an agent must infer that one looks up by ID and this one by reference.

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 reference-based lookup is the natural choice when you hold a reference, and the 'unique per mode' note hints at scoping. There is no explicit when-to-use versus `get_refund`, no prerequisites, and no statement about mode requirements.

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