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

With no annotations, the description carries the full burden and mostly succeeds: it states the call is free, creates no charge, runs no paid API, and contacts no facilitator — plus that the fingerprint itself is bearer material and must not be the raw signature. The remaining gap is failure behavior (what a not-found fingerprint yields) and whether the lookup is authenticated or rate-limited.

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?

Three sentences, front-loaded with the triggering scenario before the mechanics and the safety constraints. Every clause carries information: condition, derivation, input format, safety profile, secret-handling warning — no restatement of the tool name or 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?

No output schema and no annotations, so the description must carry return semantics — and it never states what the response looks like on success (presumably the receipt UUID) or on a miss (unknown fingerprint, ambiguous match). The input side is complete and the security posture is well covered, but the return contract is left implicit.

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 coverage is already 100%, so baseline would be 3, but the description earns more by specifying the derivation (SHA-256 of the exact original header, computed locally), the exact accepted form (64-character hex), and reinforcing the prohibition on passing the raw signature. It does not address case-normalization or what to do if the original header was altered.

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?

Specific verb+resource combination: recovers a lost receipt UUID by supplying a SHA-256 fingerprint of the original Payment-Signature header, with a clear triggering condition (payment reserved, response lost). It does not, however, differentiate itself from plausible siblings such as kevaremesh_check_owned_receipt or kevaremesh_reconcile_gateway_receipt, leaving the agent to infer the boundary.

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 triggering condition: use when an authorized x402 payment was reserved but the network response carrying the receipt UUID was lost. No exclusions or named alternatives are given, so an agent must still decide on its own between this, check_owned_receipt and reconcile_gateway_receipt.

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