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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, and the description reinforces rather than contradicts them by asserting no network request, fetch, money movement or external write. It adds genuinely useful behavior beyond the annotations: payment terms (0.10 USDC on Base via x402 exact, 10 signed-wallet free calls per rolling 30 days), the X-Wever-Wallet-Proof binding to the exact JSON arguments and route, and the Ed25519 signed receipt. It does not explain why idempotentHint is false (repeat calls presumably re-bill), which is a meaningful omission for a paid tool.

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 body is a single sprawling sentence that re-enumerates schema fields at length and repeats the production-path framing twice ('production asset by production asset', then the long list of risk types). The payment, auth and endpoint details are valuable, yet the whole could be roughly halved without losing routing or behavioral information.

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?

There is no output schema, so the description carries the return-value burden and does so adequately: it names the three verdicts (production_reachable, isolation_unverified, isolated), the report's per-asset path findings with fixes, and the Ed25519 signed receipt. For a nested five-parameter, paid, read-only audit tool this is close to complete; only the report's structural shape and repeat-call billing behavior 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?

With 80% schema description coverage, the baseline is 3; the description earns an extra point by explaining the semantic intent of the nested structures — where each credential is accepted and how it is made, each system's environment, reachability, internet exposure, what it accepts, the access granted and its rate limit, and the sandbox's outbound default. This maps the caller's real-world facts onto the nested fields rather than just restating them, though it does not cover the optional `label` parameter.

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 a sandbox/test environment design and receive a signed isolation report — and enumerates exactly what the input covers (credentials, systems, data, outbound default). It explicitly routes the adjacent cases to wever_escape-path-check and wever_firewall-order-check, so the agent can separate this tool from its nearest siblings without opening either 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?

Clear conditions are given for the two closest alternatives: a single sandbox-to-production route belongs to wever_escape-path-check, and ordering inside one payment flow belongs to wever_firewall-order-check. What is missing is guidance against the much larger sibling set of governance checks (identity, permission ledger, credential requirements), leaving some ambiguity for an agent deciding between overlapping audit tools.

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