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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, and the description reinforces this with concrete specifics: it reads only the material in the call, makes no network request, fetch, wallet or merchant lookup, and performs no order, payment or external write. It goes further with behavior the annotations cannot express: the POST /api/policy-replay-check route, the X-Wever-Wallet-Proof binding to the exact JSON arguments and route, and the Ed25519 signed receipt returned with the report.

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 correctly: the core operation and its outputs come first, then the alternative-tool disambiguation, then access, auth and reference links. Nearly every sentence carries operational weight, though the parenthetical rules inventory is long and the trailing contract/URL pointers add bulk that is useful once but not on every read.

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, signed, read-only replay tool with no output schema, the description covers everything an agent needs before calling: inputs required (rules plus history), the verdict vocabulary, what the report names, pricing and free-call allowance, the wallet-proof header binding, and pointers to the contract and human page. Nothing material is left for the agent to guess.

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 documents the four top-level parameters and the nested rule and history fields. The description's enumeration of rule kinds and its note that rules may optionally be limited to counterparties, categories or services adds some framing, but it largely restates the rule enum rather than explaining how values interact (for example ordering, precedence between a block list and a period cap, or how 'per' grouping changes counting). 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?

The description names a specific verb and resource: it takes proposed structured rules plus a batch of past traces and replays the rules over that history in time order to produce per-rule verdicts. It also enumerates what the rules can express (per-action caps, period caps per day/week/month/total, allow/block lists, approval thresholds) and states the exact outputs (would_block, would_need_approval, no_change) with counts and named records, so the agent knows precisely what it gets.

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 an explicit routing rule: 'Supplied history only: a live x402 challenge is wever_payment-policy-check,' which cleanly separates this offline replay tool from its nearest live-check sibling. It also states the access model (paid 0.10 USDC per call, 10 free signed-wallet calls per rolling 30 days). It does not differentiate from the other policy siblings such as wever_policy-fit-check, wever_spending-policy-check or wever_treasury-policy-check, leaving that inference to the agent.

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