Reject Payment

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

The destructiveHint annotation already flags this as irreversible; the description reinforces that and goes further by naming the consequence ('the order is not delivered') and the authorization prerequisite. It adds meaningful context beyond the annotation, though it says nothing about side effects on related records or the response.

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: the action and its effect come first, followed immediately by the authorization condition and the irreversibility warning. Nothing is redundant.

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 one-parameter destructive action with an existing annotation, no output schema, and no nested objects, the description covers the essentials an agent needs: what it does, when it is permitted, and that it cannot be undone.

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?

Single orderId parameter fully documented in the schema (100% coverage), so the schema carries the load. The description's 'payment on hold' framing implies the kind of order the ID must reference but adds no format or syntax detail. 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 (reject) and resource (payment) plus the precondition state ('on hold'), and the outcome clause ('the order is not delivered') makes it the clear counterpart to the sibling confirm_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?

Explicitly gates invocation on creator approval ('Only do this after the creator has said so'), which is real when-to-use guidance. It stops short of naming the alternative path (confirm_payment) for the agent to weigh against, so it is clear context rather than full routing.

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