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

With no annotations, the description carries the full burden and does disclose real behavior: this is a request, not an automatic refund, and 'The Kiosq team reviews it' signals human, asynchronous adjudication. It does not say what happens to the order while under review, whether the refund is full or partial, or what the approval criteria are.

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?

Two sentences, no filler, with the guarantee context and the precondition front-loaded before the review outcome. The 'Kiosq guarantee:' lead-in is slightly ornamental but does convey platform policy.

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 two-parameter mutation with no annotations and no output schema, the description covers prerequisites and process but leaves the note parameter unexplained and the post-submission outcome (timing, decision, order state) unaddressed. Adequate to select the tool, thin for invoking it correctly.

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 50% — order_id is documented as a UUID, but the required 'note' field (10-2000 chars) has no schema description and the tool description never mentions it. The brief-mismatch framing lets an agent guess the note should explain the failure, but that is inference rather than stated guidance.

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 ('request a refund') plus the triggering condition ('result still does not match the brief'). It implicitly distinguishes itself from the sibling request_revision by requiring that the free revision already happened, though it never names that sibling outright.

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?

'after the free revision' and '(requires buy)' establish a clear prerequisite ordering — revision first, refund only afterwards, and only on a purchased order. What's missing is an explicit exclusion (e.g. do not use before exhausting revisions), but the sequencing is unambiguous enough to act on.

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