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

Beyond the annotations, the description discloses important behavior: the tool may update status and send notifications, returns an approval URL first, and performs no change until separate human approval. This adds meaningful async flow context that annotations alone do not convey. Slightly more detail about what 'may update status' entails could push it higher.

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?

Four compact sentences, each earning its place: the action, the read-only alternative, the approval-URL first behavior, and the idempotent retrieval instruction. Information is front-loaded and the description is dense without being bloated.

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?

The description covers the core async flow, the read-only alternative, and reuse for result retrieval, and an output schema exists to define return values. A small gap is that it doesn't clarify what qualifies as an 'owned payment' or any prerequisite state, but this is not likely to block a correct invocation.

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 0%, so the description must compensate for explaining requestId and details, but it only says to 'reuse the identical requestId and details'. It does not explain that details contains id and signature, what signature represents, or how these values should be obtained. This is minimal compensation for a nested two-parameter 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 a specific action ('Trigger on-chain verification for an owned payment') and distinguishes it from the read-only sibling payment_get by explicitly naming that alternative. The tool's role as a verification/approval trigger rather than a listing or creation tool is unambiguous.

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?

It explicitly directs agents to use payment_get for read-only polling, which is a clear when-not/when-to alternative. It also explains the required workflow: the call returns an approval URL first, no change occurs until human approval, and the same requestId and details must be reused to retrieve the result.

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