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

Annotations already declare read-only, closed-world, non-destructive, non-idempotent, and the description reinforces rather than contradicts them: "Reads only the material in the call: no network request, fetch, money movement, message, sharing, configuration change or external write." Beyond annotations it discloses the paid URL and price (0.10 USDC on Base via x402 exact), the shared 10 free signed-wallet calls per rolling 30 days, the X-Wever-Wallet-Proof binding requirement, the signed Ed25519 receipt, and the four possible verdicts.

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?

The information density is high and the trailing sentences (verdicts, route, read-only guarantee, payment terms, contract link) each carry weight, but the first sentence is a single sprawling clause that lists six dimensions twice — once as rehearsal attributes and again in the report summary — which is avoidable redundancy. Splitting the enumeration into a short lead plus a bullet-style list of the dimensions would preserve every fact at half the reading cost.

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 complex tool with a nested three-parameter schema, no output schema, and a monetary side effect, the description covers what an agent needs: inputs, the four verdicts, the signed receipt in the response, the exact price and free-call allowance, the required wallet-proof binding, and the read-only guarantee. Nothing material about calling it correctly is left to inference.

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 67% and the nested enum fields already carry their own descriptions (price, result, timing, payment_flow, failures, cost, result_fields), so the description largely restates them in prose rather than adding new meaning. It does usefully frame the call group as name, endpoint, amount, network and result fields, clarifying the shape of the nested object, but adds no format, constraint, or example beyond what the schema already supplies. Baseline 3 is right here.

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 action (submit one paid call plus its rehearsals) and the specific artifact returned (a signed report naming which rehearsal proves each dimension). It is clearly distinguishable from adjacent siblings, but the opening sentence is a 150-word run-on that buries the verb under an enumeration of rehearsal attributes, so the purpose has to be reassembled rather than read.

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 explicitly routes two adjacent questions elsewhere: wever_provider-readiness-check covers whether a rehearsal exists at all, and wever_sandbox-isolation-check covers whether a test environment reaches production. That is real alternative-naming, not implied usage. It stops short of stating when this tool should be skipped, such as for an already-verified or unpaid call, and never warns that a second call re-charges.

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