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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds useful behavioral context by saying suggested matches include a reason and that refund_id returns the full link, though "that link whole" remains vague about the actual response shape.

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 description is short, but it is not front-loaded with a clear action and the fragment "With refund_id: that link whole" is awkward. It is concise without being easy to parse.

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 read-only retrieval tool with rich annotations, the description covers both listing and detail modes well enough to call it. It still leaves the exact return contents and suggested-match behavior under-explained.

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 schema already documents refund_id with an example. The description adds only that supplying refund_id returns the whole link, which is useful but minimal beyond 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?

The description conveys the refund resource indirectly through phrases like "Money back linked to the purchase it reverses" and distinguishes the optional refund_id detail mode. However, it never states a clear verb such as list or get, and the phrasing is cryptic enough that an agent may need to infer the tool's exact purpose.

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?

It implies two modes: without refund_id, list refunds plus suggested matches; with refund_id, retrieve one link in full. But it gives no guidance on when to use this instead of siblings like purch_link_refund, purch_unlink_refund, or o2c_refund.

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