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

Goes well beyond the supplied annotations: it declares no network request, no fetch, no money movement, no messages, no sharing, no configuration change and no external write, which independently corroborates readOnlyHint and openWorldHint=false. It also discloses the commercial and auth behavior an agent must plan for — 0.10 USDC per call on Base via x402 exact, 10 signed-wallet free calls per rolling 30 days, and X-Wever-Wallet-Proof bound to the exact JSON arguments and route — and states the report carries an Ed25519 signed receipt. Also correctly flags non-idempotency implicitly via the paid per-call model and signed receipt per invocation.

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?

Purpose and input shape are front-loaded before the routing, verdict, endpoint, pricing and auth details, which is the right order. The middle sentence is a long chained clause and the endpoint/pricing/contract/human-page tail is dense, but essentially every element is operational information an agent needs rather than filler.

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 tool with no output schema, the description still describes the return shape (signed report naming each mismatch with percent price delta and each uncompensated purchase) and the verdict vocabulary. Combined with disclosed cost, auth binding, read-only scope and sibling routing, an agent has everything needed to decide, invoke and interpret without opening the contract page.

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 coverage is 100%, so the baseline would be 3, but the description adds real meaning: it explains that each purchase carries a quoted/recorded set and a governing published-or-contract set, that the relevant fields are price, scope and cancellation, that each side records where it came from (mapping to `source`), and that `compared_before_payment` is the pre-payment comparison flag. The `paid` boolean is never explained in prose and only inferable from the report sentence, which keeps this from a 5.

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 purchases with quoted and governing terms so the two can be compared, and names the exact artifacts produced (mismatches with price difference in percent of governing price, plus uncompensated pre-payment purchases). It also enumerates the four verdicts (terms_mismatch, compared_late, match_unverified, terms_match), so an agent knows precisely what class of answer this tool returns versus a generic check.

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?

Explicitly routes three adjacent cases away: single-service terms go to wever_service-terms-check, time-varying terms to wever_terms-change-check, and money-vs-invoice to wever_settlement-reconciliation-check. What's missing is a positive trigger sentence ("use this when a purchase already carries both a quoted and a governing term set") and any statement of when not to call it at all, but the sibling partition is strong.

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