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

Above the annotations bar: the description adds payment terms (0.10 USDC per call on Base via x402 exact, 10 free signed-wallet calls per rolling 30 days), an authentication requirement (bind X-Wever-Wallet-Proof to the exact JSON arguments and route), and a return guarantee (Ed25519 signed receipt). The 'no network request, fetch, money movement... or external write' sentence largely restates readOnlyHint/openWorldHint, but the cost and auth disclosures are genuinely additive.

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 is front-loaded, but the description is a dense multi-clause run-on that packs purpose, verdicts, safety claims, transport, pricing and links into one block. The enumeration of decision kinds (arithmetic, threshold, eligibility, limit, rounding, conversion, date, formatting, extraction, classification) duplicates the schema enum verbatim and earns no place, and 'Contract:'/'Human page:' links pad the tail.

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-report tool with no output schema, the description covers what goes in, what comes back (a signed report naming unchecked model decisions and the smallest reassignment, with a verdict of model_computes, unchecked_output or deterministic_core), auth, and cost. Only the exact report shape and whether repeat calls are cached (idempotentHint is false) remain unspecified.

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 label, decisions, components and every nested field. The description paraphrases the same structure - kinds of decision, who makes it, the check, what the output is used for - and adds only marginal meaning such as 'the smallest reassignment for each'. Baseline 3 applies since the schema does the heavy lifting.

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 states a specific verb and resource: submit a system design (decisions + deterministic components) and receive a signed report naming where model judgement should be code, plus a verdict. That is far more precise than the title 'Deterministic core check'. It never names a sibling tool as an alternative, but among the many wever_*-check siblings the resource is distinctive enough that an agent can identify it.

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?

Usage is implied by 'submit a system design that splits work between a model and code' - the precondition (a design exists, split between model and code) is visible, but there is no explicit when-to-use versus when-not, and no routing to any of the numerous related check siblings. The agent must infer the trigger condition from the description's framing.

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