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

Annotations only supply readOnlyHint=true, so the description's disclosure of the return shape ({refunds:[...]}) is genuinely additive, especially since no output schema exists. It still says nothing about pagination, result limits, or error behavior for a list endpoint, which is the main remaining gap.

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?

Three short sentences, front-loaded with the action and scope, then the return shape, then the endpoint. Nothing is padded or redundant.

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 single-parameter read tool with no output schema, the description covers what it returns and where it maps in the API surface. The only missing element is list behavior such as pagination or ordering, which an agent may need for large refund sets.

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% and the single parameter is documented there with its tr_ prefix format. The description only echoes transaction_id in the path template, adding no syntax or constraint information beyond the schema — baseline 3 applies.

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 and resource — 'List all refunds recorded against a transaction' — and the endpoint line confirms read semantics. It implicitly contrasts with the sibling numeral_create_refund, but never names it or any other sibling, so the differentiation is left to inference.

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 use this versus alternatives, nor any prerequisite or exclusion. The only 'guidance' is the required transaction_id, which the schema already imposes.

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