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

Annotations already declare destructiveHint=true, so the safety profile is covered; the description adds real value by explaining the concrete effect (releases the hold on the customer's funds) and giving the underlying API route. It stops short of stating prerequisites such as required API scope, error cases, or whether a void can be undone.

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 compact sentences with zero filler; the destructive effect and the state precondition are front-loaded before the endpoint reference. Every clause carries information an agent can act on.

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 four-parameter mutation tool with no output schema, the description supplies the essential semantics: what is voided, in which state, and what the side effect is. It omits any hint of the returned void status or idempotency behavior, which would have closed the remaining gaps at no cost.

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 100%, so id, metadata, reference, and idempotency_key are all documented in the schema already, which sets the baseline at 3. The description adds no parameter-level meaning beyond implying the payment id is the path segment, so it neither helps nor hurts.

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 (VOIDS/cancels) against a named resource (payment) and adds the qualifying state 'authorized but not yet captured', which is exactly what separates it from capture and refund operations. It does not name a sibling tool explicitly, so an agent must infer the boundary from the state condition rather than being told.

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 phrase 'authorized but not yet captured' functions as a clear when-to-use precondition and implies when it should not be used (captured payments need refund instead). However, it never names checkout_refund_payment or checkout_capture_payment as the alternatives for those other states, leaving the routing inference to the agent.

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