Refund POS Sale

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

Beyond annotations (destructiveHint=true), the description adds key behavioral details: the action is irreversible, funds return to the original payment method, and confirm is a mandatory safety check. This fully informs the agent of consequences.

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 description is concise with two clear sentences in English and a Spanish translation. It front-loads the core action and key requirements. The bilingual content is necessary but adds length; still efficient overall.

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 action, the description covers irreversibility, payment method, confirm requirement, and partial refund. It does not detail return values, but an output schema exists. Sibling differentiation (e.g., refund_deposit) is missing but the tool name and description sufficiently narrow context.

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 baseline is 3. The description reiterates the purpose of 'confirm' and 'amountCents' but adds no new meaning beyond the schema. The 'reason' parameter is not mentioned, though its enum values are clear in the schema.

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?

The description clearly states the action ('Refund a POS sale'), resource ('POS sale'), and scope ('in full or partially'), distinguishing it from sibling tools like refund_deposit. The verb 'refund' and resource 'POS sale' are precise.

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 description specifies when to use this tool (for refunding POS sales) and includes a critical prerequisite ('MUST pass confirm=true'). However, it does not explicitly contrast with alternatives like refund_deposit or state when not to use, leaving room for ambiguity.

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