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

Goes well beyond the annotations: fetch behavior (one GET, no redirects, public DNS only, 512 KB cap), cost model (0.10 USDC on Base via x402 exact, 10 signed-wallet free calls per rolling 30 days), the X-Wever-Wallet-Proof binding requirement, and the Ed25519 signed receipt. It also states the matching limit ("matches words, figures, dates and named items ... does not interpret meaning") — a materially useful expectation-setting detail.

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 is front-loaded and no sentence is pure filler, but the text is a dense chain of parentheticals and boilerplate (endpoint path, contract path, human page URL) that duplicates schema and platform metadata. Splitting the payment and provenance clauses out would make it far easier to scan.

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 carries the return-value burden and does so: it enumerates report contents (amount, currency, period, seat basis, billing cycle, limits, features, other priced items, flagged conflicts with offsets) plus the signed-receipt guarantee. Inputs, cost, auth header and limits are all present, leaving nothing an agent needs unknown before calling.

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 100% and every parameter, including the format default heuristic, is already documented in the schema, so the description mostly restates it ("one public HTTPS page read once with GET"). The only added meaning is the oneOf intent and the read-once constraint, so baseline 3 applies.

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 verb and resource ("submit a pricing page ... The signed report lists the tiers with their prices, limits and features") and enumerates exactly what the report detects (same tier/item priced two ways on the same basis, a limit stated with two different values). This separates it cleanly from sibling evidence checks such as wever_terms-evidence-check or wever_benchmark-evidence-check without opening their schemas.

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 input conditions are explicit: exactly one pricing page as text or as a public HTTPS URL, and the tool's boundary ("no account access, no merchant contact") tells the agent what this check cannot be used for. It never names an alternative tool or a when-not condition, so the routing decision against the many sibling evidence-check tools is left to inference.

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