marketplace_refund_payment

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

Annotations already disclose destructiveHint=true, readOnlyHint=false, openWorldHint=true and non-idempotence, so the safety profile is largely covered. The description adds one genuinely useful behavioral constraint beyond that – the exact confirmation phrase gating the operation – but omits what gets destroyed, permission requirements, and whether plan mode mutates anything. Note the tension: confirmation is optional in the schema though the description calls it required.

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 short sentences, front-loaded with the action and followed by the key constraint. No filler, though it is arguably under-written for a destructive 5-parameter tool rather than merely concise.

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 payment tool with 5 parameters, 20% schema coverage and no output schema, the description is too thin: it omits the plan/apply workflow, the confirmation phrase value, caller-ownership requirements for partner_id, and any notion of what a refund does to existing state.

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 only 20%, so the description must compensate and does not: partner_id, application_id and payment_id get no explanation, and the enum is plan/apply while the prose says "plan or report," a mismatch that could confuse mode selection. Only the confirmation parameter gains any meaning from the text.

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 (refund) and resource (Marketplace payment) and flags a dual plan/apply capability, so an agent knows exactly what this does. It does not differentiate itself from the closest sibling, marketplace_record_payment, or clarify how the two relate (e.g. refund as reversal of a recorded payment).

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?

"Plan or report" implies a two-step workflow and the requirement of an exact confirmation phrase gives a precondition, which is useful guidance. However, it never states when to use plan vs apply, when this tool should be chosen over marketplace_record_payment, or that confirmation is only needed in apply mode.

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