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

Annotations already declare readOnly/openWorld=false, but the description adds material context the agent cannot get elsewhere: it reads only supplied material with no network request, fetch, money movement or external write; it costs 0.10 USDC per call on Base via x402 exact with 10 signed-wallet free calls per rolling 30 days; the X-Wever-Wallet-Proof header must be bound to the exact JSON arguments and route; and the report carries an Ed25519 signed receipt. Slight deduction because 'no money movement' coexists with a paid endpoint without explaining how the x402 charge is settled relative to that claim.

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?

Purpose and comparison logic are front-loaded, then alternatives, then verdicts, then operational metadata — a sensible order with no filler. The mismatch sentence is a long run-on list, and the pricing/contract/URL tail is dense, so it is efficient but not maximally scannable.

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?

With no output schema, the description still names the four possible verdicts, states that a signed report is returned with an Ed25519 receipt, points to the contract endpoint and human page, and discloses payment and auth requirements — enough to call it correctly. It does not describe the report's internal shape (per-field comparison rows, difference and share values), which would have closed the last gap.

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 only 33% and the schema is deeply nested, yet the description enumerates nearly every meaningful field of both objects (amount, asset, network, quantity, unit price, delivered_means, quoted_at/expires for the quote; amount, asset, network, quantity, delivered_quantity, settled_at, reference for the charge) and explains how unit_price × quantity and lapse timing are used as checks. It omits the optional `label` parameter and gives no guidance on numeric-string amounts or accepted timestamp formats.

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 and resource: it submits a quote and a settled charge, then compares amount, asset, network and quantity field by field and names each mismatch. It also enumerates the exact verdicts (price_mismatch, quote_gaps, price_unverified, price_true) and names four sibling tools it is not (wever_terms-match-check, wever_endpoint-honesty-check, wever_fee-reconciliation-check, wever_invoice-payment-match), so an agent can place it precisely among ~200 siblings.

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 gives explicit routing rules: quoted terms vs published terms goes to wever_terms-match-check, a live 402 challenge vs advertised terms to wever_endpoint-honesty-check, charges vs a fee schedule to wever_fee-reconciliation-check, an invoice vs a payment to wever_invoice-payment-match. The remaining case — quote vs the charge actually settled for the same call — is thereby clearly reserved for this tool.

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