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

Annotations already declare idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: who bears the cost per reason (legal guarantee vs. own policy), that changed_mind is time-boxed to a withdrawal period, and that the return surfaces as linked and appears under refunds in get_item_status. It does not contradict the annotations.

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?

Compact and front-loaded: the precondition and action come first, then reason semantics, then line selection, then the return's downstream linkage. Some sentences are heavily compressed and read as run-ons, but there is no filler.

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 9-parameter mutation with no output schema, the description covers the action, reason economics, line selection, and result linkage reasonably well. It still leaves `wants` (refund/exchange/credit) and the `other` reason unexplained, and gives only 'comes back as linked' about the response.

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 78%, so the schema mostly carries parameter meaning and a 3 is the baseline. The reason semantics (faulty/not_as_described/wrong_item as the legal guarantee vs. changed_mind as a withdrawal) add value, but the lines sentence merely repeats the schema description verbatim and the description omits `wants`, `note`, and the `other` enum value.

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+resource (send goods back / request a return) with a clear scope gate: goods must already have reached the person. That implicitly separates it from pre-delivery siblings like cancel_item, though it never names them. An agent can identify the operation without opening the 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?

The opening clause gives the triggering condition ('Once an order's goods reached your person'), which is genuine when-to-use guidance and implies when-not (before delivery). It does not explicitly route to alternatives such as cancel_item or withdraw_from_contract, so it stops short of a 5.

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