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

The annotation only carries destructiveHint=true, so the description does useful extra work by explaining the concrete effect: releasing the hold on the customer's funds. It omits whether a void can be reversed, what happens on an already-captured payment, and any idempotency/permission caveats, which is a real but modest gap.

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 clauses: the effectful clause first, then the API endpoint reference. No filler, nothing that restates the name or title.

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 single-payment mutation with no output schema, the description supplies the key operational context (state precondition, financial effect, backing endpoint). Error/failure behavior and irreversible-vs-reversible detail are the remaining omissions, but they are not required to call the tool correctly.

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 the bare id, metadata, reference and idempotency_key semantics are already fully documented in the schema. The description adds nothing about parameter behavior (e.g. that idempotency_key maps to the Cko-Idempotency-Key header), so 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 (voids/cancels), the resource (payment), and the exact state constraint (authorized but not yet captured), which cleanly separates it from checkout_capture_payment and checkout_refund_payment. An agent can pick it out of 18 siblings without opening the schema.

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' gives a clear precondition for use, so an agent knows which payments qualify. It stops short of naming alternatives or spelling out what to do for already-captured payments (refund) or already-voided ones, so it is context without explicit exclusions.

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