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

Annotations already declare readOnlyHint=true and openWorldHint=false, but the description adds substantial context beyond them: no network request, no money movement, no external write, the x402 pricing (0.10 USDC on Base, 10 free signed-wallet calls per 30 days), and the requirement to bind X-Wever-Wallet-Proof to the exact JSON arguments and tool route. It also discloses the output shape (report with an Ed25519 signed receipt) and links the contract, which are behaviors an agent needs and which annotations do not carry.

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 purpose is front-loaded, but the opening sentence is a long single parenthetical list of nine facets crammed into one clause. Operational boilerplate (endpoint, pricing, wallet-proof binding, contract and human page URLs) takes roughly half the text and could be compressed; density comes at the cost of readability.

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 nested-input, no-output-schema tool, the description covers what must be supplied, how the nested pieces are interpreted, what the report asserts, the three possible verdicts, the read-only safety envelope, and the paid/auth mechanics. Nothing material needed to call it correctly appears to be missing.

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?

The parenthetical enumerates the refund-term facets in a way that maps onto the nested schema fields (when fixed -> written, payer sees before paying -> shown_before_payment, who may request -> requesters, how decided and by whom -> decided/approver, window, destination, amount, paid_within), and 'its checkout steps with what each records' explains the flow/captures nesting. That adds meaning over the 67%-covered schema, though it never mentions the optional 'label' parameter or constraints such as length limits and ordering.

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 concrete action and resource: submit a checkout/payment setup's refund terms plus checkout steps, and receive a signed report on whether a refund rule exists before checkout and where the gaps are. It explicitly names the sibling it is not ('One purchase against a refund policy is wever_refund-eligibility-check') and lists the verdicts it produces, so an agent can separate it from the many wever_*-check tools.

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 alternative routing is explicit: multi-step checkout/payment setups go here, a single purchase against an existing policy goes to wever_refund-eligibility-check. It also states the call reads only supplied material and performs no network/write actions, which frames legitimate use. There is no explicit statement of when the tool is unnecessary (e.g. no-refund contexts), so it stops short of full when/when-not guidance.

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