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

Beyond the annotations it discloses the key behavioral facts: reads only the material in the call, no network/fetch/wallet/merchant/order/payment/external write, never re-pays, never contacts the seller, returns an Ed25519 signed receipt. It also covers operational constraints the annotations do not — 0.10 USDC per call via x402 exact on Base, 10 signed-wallet free calls per rolling 30 days, and the X-Wever-Wallet-Proof binding to the exact JSON arguments and route. This is consistent with readOnlyHint=true, openWorldHint=false and destructiveHint=false.

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?

The core instruction is front-loaded in the first sentence, but everything else is packed into one dense block with no separation between evidence requirements, output semantics, safety claims, pricing/auth mechanics, and reference links. Nearly every clause is useful, yet the absence of structure makes it harder to scan than it needs to be.

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 five-parameter tool with a nested payment object, no output schema and no enums, the description covers the input requirements, the verdict vocabulary, the next-step vocabulary, the signed-receipt return, the read-only guarantee, auth binding and the cost model. An agent has everything needed to decide to call it and to construct a valid call.

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 80%, so many fields are already documented, yet the description adds real semantic value by explaining what the report does with them — 'ties each response to the payment by its reference or by endpoint and time' — which tells the agent why payment_reference, result_reference, endpoint and timestamp matter when filling the nested objects. It does not, however, explain the top-level asset/label overrides or the amount-as-string-vs-number tolerance beyond what the schema says.

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 concrete verb and resource: submit one payment proof plus an account of the missing result, and receive a signed report that classifies the outcome as delivered, not_delivered or unresolved and names a next step (re_request_same_reference, present_proof_to_seller, treat_as_unresolved). That is far more specific than the title. It stops short of 5 because no sibling is named (e.g., wever_dispute-open, wever_refund-eligibility-check, wever_recovery-readiness-check); differentiation is only implied by 'never pays again and the seller is never contacted'.

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 clearly implies the triggering situation — you paid, the result is lost or missing, and you hold a transaction reference and response records — and enumerates the three safe next steps the output can support. What is missing is an explicit when-not or an alternative tool to pick instead when, say, you want an actual dispute opened or a refund assessed.

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