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

Adds substantial context beyond the annotations: carrier-specific refund timing (instant for unprinted USPS, pending for printed, ~1 hour for UPS), destination of funds to Account Balance, the fact that a refunded label becomes unusable, the confirmation flow, and the external-reach/API-key requirements. This is exactly the kind of side-effect and auth disclosure annotations alone do not 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 purpose and timing rules are front-loaded well, but there is redundancy: confirmation is stated twice and 'like Refund Label' restates the title. Several clauses could be tightened without losing information.

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 mutation tool with no output schema, the description covers timing, side effects, funds destination, confirmation policy, and auth needs. Nothing essential for correct invocation is missing.

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 (shipment_id) is fully documented in the schema, including its source. The description adds no parameter-level detail, so baseline 3 is appropriate given the schema does the work.

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?

Names a specific verb and resource ('Request a refund for an unused label') and frames the preconditions immediately. An agent can distinguish this from siblings like buy_label or list_shipments without opening any schema.

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?

Gives concrete conditions for use: within 28 days, label unused, and requires confirmation before each call. It does not explicitly name sibling alternatives or state when not to refund, but the timing and state preconditions are clear enough to route correctly.

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