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

Beyond the annotations it discloses paid access terms (0.10 USDC per call on Base via x402 exact, 10 signed-wallet free calls per rolling 30 days), the required X-Wever-Wallet-Proof binding to exact JSON arguments and route, and the signed-report output. That is substantial extra context, though the payment/auth mechanics are described tersely and the failure modes of a bad proof are not stated.

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 nothing is obviously padding, but the opening sentence is a ~60-word run-on that fuses purpose, input specification and output description, and the endpoint/payment/contract lines accumulate into a wall of text. It is front-loaded with the verb and resource, yet the structure could be split into scannable clauses.

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-object tool with no output schema, the description names the verdict values (unmediated_paths, coverage_unverified, fully_mediated), the three findings the signed report contains, and the Ed25519 receipt, which is close to complete. It leaves the report's actual field layout and the meaning of partial verdicts unexplained, but an agent can call it correctly from this.

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 67% schema coverage and nested objects, the description compensates by mapping prose onto the nested fields: gateway.checks, gateway.decided_by, gateway.when_down, and per-tool effect, via_gateway, direct (who reaches it directly) and traced (where calls are traced). It does not enumerate the enum values for traced or when_down, so the schema still carries some weight.

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 — submitting an MCP/tool-access architecture to receive a verdict — and enumerates the exact inputs it expects (the gateway and its checks, the allow/deny decider, fallback behavior, and each tool's effect, reachability and tracing). It also distinguishes itself from the nearest sibling by naming wever_firewall-order-check as the tool for check ordering inside a payment flow.

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 the ordering question to wever_firewall-order-check, and the 'reads only the material in the call: no network request, fetch... external write' sentence tells the agent this is a pure static analysis, which is a clear use condition. It stops short of stating when a caller should not use it (e.g. single-tool exposure, which a sibling tool-exposure-check likely covers).

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