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

Beyond the annotations it discloses that the tool reads only the material in the call — no network request, fetch, money movement, message, sharing, configuration change or external write — which is important given the POST route and the false idempotentHint. It also documents pricing (0.10 USDC per call on Base via x402 exact, 10 free signed-wallet calls per rolling 30 days), the X-Wever-Wallet-Proof requirement bound to the exact JSON arguments and route, and the Ed25519 signed receipt returned.

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?

Nearly every sentence carries real information, but it is delivered as a single dense run-on that mixes semantics, verdict names, payment mechanics, auth headers and links without paragraph or list structure. An agent can parse it, but the front-loaded purpose is quickly buried under operational detail, and repeated 'signed report/signed receipt' phrasing could be tightened.

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, multi-object check with no output schema, the definition still describes the report contents and verdict enumeration, spells out read-only scope, and documents cost, free-tier limits, wallet-proof binding and the contract/human reference URLs. Nothing an agent needs to invoke it correctly or anticipate the response appears missing.

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 only 50% and the parameters are deeply nested, yet the prose covers most of the semantic surface: per-action and period limits, allowed and blocked counterparties, who may approve exceptions, and for the approval the approver, amount, counterparty and expiry, plus taken vs proposed status. It does not explain the interaction of spent_in_period with period_limit or how free-text 'text' fields are weighed against structured limits, leaving some interpretation to the schema.

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 the specific inputs compared (standing policy set, momentary approval, action taken or proposed) and the concrete output (which instruction governs, whether the action sat inside both, and the exact conflict point). It also names the sibling it is not — 'An action against policy text is wever_policy-fit-check' — so an agent can separate it from the many neighboring policy tools 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: submit standing + approval + action here, but use wever_policy-fit-check for an action judged against policy text. It also enumerates the outcome space (outside_standing_policy, outside_approval, inside_both), which clarifies when a call is warranted. It stops short of a full when-not list (e.g. what to do if there is no approval record at all), so not a top score.

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