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

Goes well beyond the annotations: it discloses refund settlement timelines (Airmoney instant, original payment 7-10 business days), a fraud/manual-review risk when several refunds happen close together, the default per-call confirmation behavior with an opt-out, the fact that it affects other people, and the required Cotlet API key scope.

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 core facts are front-loaded, but the button metaphor is stated twice ('the same as the Request Refund button' and 'the way the Request Refund button does under Package History or Profile > Orders'), which is redundant. The trailing notes about confirmation and API keys read as appended boilerplate rather than a tight structure.

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 mutation tool with no output schema, the description covers eligibility, failure conditions, settlement timing, side-effect risk, confirmation policy and auth requirements, which is everything an agent needs to invoke it safely.

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%, so the schema already documents order_id, reason and refund_to, including the conditional rule that original_payment is only valid for installation_issues and esim_not_working. The description adds no parameter-level detail beyond that, so the 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 (request a refund on an eligible order) and anchors it to a concrete user-visible action (the Request Refund button in Package History or Profile > Orders). An agent knows exactly what the tool does and that it is the only refund path in the Airalo family.

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 explicit eligibility conditions (only eligible orders; expired or fully used eSIMs are not eligible and the call errors), plus a required user-confirmation workflow before each call. It does not name alternative tools, but no sibling competes for this intent, so the gap is minor.

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