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

Annotations already declare readOnlyHint and idempotentHint. The description adds a nuance that the inspection trail is only available after arrival, which is helpful behavioral context. No contradictions.

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?

Single, focused sentence with no filler. Every word contributes to explaining the tool's purpose and expected response contents.

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 simple get-by-id tool, the description fully covers what the agent needs: the parameter, the resource type, and the key response fields. No output schema is provided, but the description compensates by listing the included data.

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?

The sole parameter return_id is fully described in the schema as 'UUID of the return to fetch.' The description reinforces 'by id' without redundancy, clearly linking the parameter to the action.

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?

Clearly states the action ('Fetch a single return by id') and enumerates the response contents (reason, status, restocking fee, refund ledger, inspection trail). This distinguishes it from sibling tools like returns_list and returns_get_label.

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?

Implicitly indicates usage for a single specific return rather than a list, and notes 'once the parcel has arrived' which hints at timing. Does not explicitly name alternatives, but the context is sufficient.

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