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

Beyond the annotations (readOnly/openWorld=false/idempotent=false/destructive=false), the description discloses the pricing and access model — 0.10 USDC per call on Base via x402 exact, shared 10 signed-wallet free calls per rolling 30 days — plus the auth requirement to bind X-Wever-Wallet-Proof to the exact JSON arguments and tool route, and the Ed25519 signed receipt in the response. It also caps the epistemic scope ('matches words, figures, dates and named items ... does not interpret meaning'). These are exactly the operational facts an agent needs and cannot read from structured fields.

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 with the purpose and the brief's contents, and every block (scope limits, payment, wallet binding, matching limits, endpoints) carries information. The cost is density: one long run-on enumeration with billing and auth details wedged mid-paragraph, and trailing endpoint/URL links that could be a separate line. Minor structural waste, not padding.

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?

There is no output schema, and the description compensates fully by specifying the brief's sections, the quoted-value behavior, the enumerated output, the Ed25519 receipt, and the matching-only fidelity caveat. Combined with payment, auth binding, and input scope, an agent has everything required to call it correctly and predict the response shape.

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 explains text (one excerpt, up to 256 KB), label (optional name recorded in the brief), and format (html reduces markup, defaults to html when text starts with a tag). The description repeats the one-excerpt constraint but adds no new syntax, size, or format guidance. Baseline 3 is appropriate.

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 one contract excerpt') and then enumerates exactly what the produced brief contains: parties with roles, term with effective/end dates and length, renewal kind/period/notice, termination grounds/notice/cure/fees, and payment amounts/terms/frequency/late charges, each quoted, plus explicit gaps. It also distinguishes itself from comparison-style siblings by noting a single excerpt is submitted and that the report 'does not interpret meaning beyond that matching'. An agent can tell what it will get without opening any schema.

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 contract excerpt' and 'Reads only the material in the call: no page fetch, no account access, no merchant contact and no money movement' sketch the boundary conditions. However, there is no explicit when-to-use versus the nearby wever_contract-diff-check, wever_terms-evidence-check, or wever_counterparty-brief, and no stated prerequisites beyond the payment mechanics. An agent must infer routing from the single-excerpt scope.

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