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

Beyond the annotations (readOnly, non-destructive, non-open-world), the description discloses the paid path (0.10 USDC on Base via x402 exact), the 10 signed-wallet free calls per rolling 30 days, the required X-Wever-Wallet-Proof binding to exact JSON arguments and route, and an Ed25519 signed receipt on the report. Crucially it bounds competence: the report 'matches words, figures, dates and named items' and 'does not interpret meaning beyond that matching'. That is precisely the context 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?

The purpose and output shape are front-loaded, then operational constraints (payment, wallet proof, receipt, matching limits) follow in a logical order with no filler sentences. It is dense and long, and the pricing/contract/human-page URLs could be compressed, but every sentence carries actionable information for an agent deciding whether and how to call.

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 paid, signed-output tool with no output schema, the description is unusually complete: it enumerates the report's fields, the receipt type, the payment model and free tier, and the epistemic limit of the analysis. The remaining gap is failure behavior — what happens on insufficient payment, an oversized or empty excerpt, or an unparseable HTML format — which matters given a 262 KB cap and a metered endpoint.

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%, including the enum and default logic for format, so the schema already carries parameter semantics and the baseline is 3. The description adds only indirectly relevant meaning: 'one policy excerpt' reinforces the single-document constraint and the label is implied by the signed brief, but no parameter is explained beyond what the schema states. No compensation is needed, but no extra value is delivered either.

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 names a concrete verb and resource ('submit one policy excerpt') and spells out the produced artifact in detail: coverage, exclusions as items, limits by kind with amounts, claim conditions with time limits, each quoted, plus gaps the excerpt omits. This is far from tautological. It loses the top score only because it never names a distinguishing sibling (e.g. wever_policy-fit-check or wever_warranty-check), so the agent must infer the boundary from the output description alone.

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 is implied rather than stated: 'submit one policy excerpt' plus the enumerated output tells an agent what input belongs here, and the 'reads only the material in the call' line rules out account- or URL-based variants. There is no explicit when-to-use/when-not section and no alternative named for scenarios like comparing a policy against a need, which is what sibling tools such as policy-fit-check appear to cover. The reader is left to infer routing.

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