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

Beyond the annotations the description discloses the cost model (0.10 USDC per call on Base via x402 exact, 10 signed-wallet free calls per rolling 30 days), the auth requirement (X-Wever-Wallet-Proof bound to the exact JSON arguments and route), and the return artifact (report with an Ed25519 signed receipt). It also sets a real expectation limit — matching of words, figures, dates and named items only, without interpreting meaning — which is exactly the kind of behaviour an agent needs before relying on the result.

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?

It is front-loaded: purpose first, then the report's decision points, then payment/auth, then scope limits. The sentences are dense and occasionally run long, but nearly every clause (matching limits, contract path, human page) carries operational value, so little is wasted.

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, nested-schema tool with no output schema, the description compensates well: it summarises the report's contents (each period, coverage and exclusion mismatch with quotes), the receipt, the cost and the proof header. An agent has enough to call it correctly and to know what it will get back.

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 prose walks through nearly every nested claim field (issue, purchase date, optionally delivery date, claim date, part, cause, remedy, stated warranty length) and explains the meaningful dependency that delivery date matters when the terms count from delivery. Only terms_label and format are left entirely to the schema, and coverage is already 75%.

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 (submit a warranty claim plus its terms, get a signed report that checks period, coverage, exclusions and remedy), and it enumerates exactly what the report decides. It is clear what the tool does, but it never contrasts itself with near-neighbours such as wever_claim-evidence-check, wever_terms-evidence-check or wever_refund-eligibility-check, so sibling selection still requires inference.

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: the agent learns the tool must be fed the claim and the terms text and that it reads nothing else ('no page fetch, no account access'), which usefully tells it to gather material first. There is no explicit when-to-use, when-not-to-use, or alternative-tool guidance against the many adjacent evidence-check tools.

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