Refund subscription invoice

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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the safety profile is largely covered. The description adds genuinely useful context ('Local approval required; no automatic replay'), but does not explain what state changes on failure or which permissions are needed beyond approval.

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 tight sentences with no waste; the refund-mode intent is front-loaded ahead of the approval and replay caveats.

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 destructive, non-idempotent, open-world tool with 7 params and no output schema, the description is thin: it omits error/partial-failure behavior and the refund_order alternative. Annotations carry the safety burden, so it is adequate but not complete.

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 86%, so the schema already documents nearly all parameters, including the amount/full_refund mutual exclusivity and the confirm flag. The description only loosely mirrors the partial-vs-full distinction without adding syntax or format detail, so baseline 3 is appropriate.

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 ('issue/refund') and the resource via its name, and distinguishes the two modes (partial vs full refund). However, it never names the sibling refund_order, so an agent must infer from the tool name alone which refund target applies.

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?

'Issue the exact requested partial refund, or an explicitly named full refund' implies the condition selecting each mode, but there is no explicit when-to-use guidance, no exclusion of alternatives like refund_order, and no prerequisites beyond the approval note.

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