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

Annotations already declare destructive, non-idempotent and open-world, and the description meaningfully extends beyond them: 'submit once' reinforces non-idempotency, 'including after a timeout' rules out retry on the riskiest failure mode, and 'Acknowledgement is not settlement' warns that a success response does not mean funds settled. That last point is genuinely non-obvious behavioral context no annotation conveys.

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 short sentences, front-loaded with the precondition, with each sentence carrying a distinct constraint (precondition, single-submit, ack-not-settlement, follow-up/no-retry). No filler.

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, retry-sensitive payment submission, the description covers the critical when-to-call, follow-up, and retry-safety behavior well. The remaining gap is the origin of handoffId and how to obtain it, which matters for a mutation with 0% param coverage.

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?

With a single parameter at 0% schema coverage, the burden falls on the description, which partly compensates by framing handoffId as the reference to the 'server-saved proof.' However, it does not explain the 64-hex pattern or where the handoffId originates (presumably create_wallet_handoff/prepare_wallet_signature), so an agent still cannot fully infer the value's source.

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 states a specific verb (submit) and resource (the server-saved payment proof), with a clear precondition of the owner signing 55 USDC in Phantom. An agent can tell this is the settlement-submission step rather than the preparation or status-check siblings, though it never names prepare_wallet_signature as the preceding step, leaving the pipeline slightly implied.

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?

Explicit when-to-call ('Only after the owner explicitly signs'), explicit follow-up ('Always follow with get_wallet_payment_status'), and explicit prohibition ('never automatically retry submission, including after a timeout'). It names the alternative sibling for status and the timeout edge case, leaving little to inference.

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