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

Goes well past the annotations: no page fetch, no account access, no merchant contact, no money movement; a paid URL at 0.10 USDC per call via x402 with 10 signed-wallet free calls per rolling 30 days; and a required X-Wever-Wallet-Proof header bound to the exact JSON arguments and route. It also bounds the analysis itself — word, figure, date and named-item matching only, no interpretation of meaning — which is exactly the kind of behavioural disclosure annotations cannot 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?

Front-loaded with purpose, then the read-only scope, pricing, auth binding and return shape in a logical order. Frequent em-dash and semicolon packing makes individual sentences heavy, and the trailing contract/human-page URLs are of marginal operational value, but almost every clause carries information an agent needs.

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: a report marking each claim supported, contradicted or never mentioned, with quotes, plus an Ed25519 signed receipt. Payment mechanics and auth binding are covered. What is missing is failure behaviour — what happens on insufficient funds, rejected wallet proof, or oversized input — which matters for a paid, non-idempotent 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 description coverage is 100%, so the schema already documents claims, evidence and format including the anyOf variants and size limits. The description adds a little semantic colour by specifying that formats like CSV, JSON and XLSX and durations in any unit are matched as named items. It contributes no syntax or splitting detail beyond what the schema already supplies, so the baseline of 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 specific verb and resource: submit data export/portability claims about formats, scope and timing and receive a signed report marking each claim supported, contradicted or never mentioned. The domain (export/portability) is narrow enough to be actionable. It never names a sibling, though, and this catalog contains near-neighbours such as wever_data-evidence-check and wever_privacy-evidence-check that an agent would need to distinguish on its own.

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?

Usage context is implied rather than stated: the description says what material to supply and that it reads only what is passed in, which tells the agent the shape of a valid call. It gives no explicit when-to-use/when-not and no routing advice against the many other *-evidence-check siblings. The agent must infer selection from the domain wording alone.

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