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

Annotations already declare readOnly, non-open-world, non-destructive, non-idempotent, but the description adds substantial context beyond them: reads only call-supplied material with no network, wallet or merchant lookup, costs 0.10 USDC per call on Base via x402 exact, shares 10 free signed-wallet calls per rolling 30 days, requires X-Wever-Wallet-Proof bound to the exact JSON arguments and route, and returns an Ed25519 signed receipt. That is a meaningful auth, cost and output-integrity disclosure that annotations do not carry. The only minor gap is that the receipt/report structure is not described, though the contract URL partly covers that.

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 core action and the report structure, and every block (comparison scope, sibling routing, verdicts, payment/auth, output) is load-bearing. It is dense and somewhat run-on, with the payment and contract boilerplate occupying as much space as the functional description, but nothing is clearly redundant.

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 nested, 4-parameter tool with no output schema, the description covers input shape, output shape (labelled sections, before/after figure, verdict values), signed receipt, payment terms and auth binding. An agent has everything needed to invoke it correctly and interpret the result.

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 50%, with the object-level properties (original, current) and their title/effective_date fields undocumented in the schema. The description compensates by explaining that original is 'the version in force at purchase or signing', current is the current version, and each may carry an effective date 'where stated', plus the role of the comparison date. That raises it above the coverage baseline, though it does not say what a missing effective date implies for alignment.

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 opening sentence states a specific verb and resource ('submit two versions of the same terms, policy or agreement text...and the comparison date') and the following sentences describe exactly what the report contains (sections split, aligned, changed/added/removed with buyer-impact labels and a 'before and after' figure). It also explicitly names the two nearest siblings it is not, so an agent can separate it from wever_terms-evidence-check and wever_contract-diff-check without opening a 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?

It gives explicit routing: two-version comparison belongs here, single-document evidence goes to wever_terms-evidence-check, and contract redlining goes to wever_contract-diff-check. It also states the verdict space (buyer_impact_changes, other_changes_only, no_changes), so the caller knows what outcome categories to expect before choosing the tool.

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