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

Annotations already mark this read-only and closed-world, but the description goes well beyond them: it states no network request, fetch, money movement, message, sharing, configuration change or external write occurs, that the call costs 0.10 USDC via x402 with 10 free signed-wallet calls per 30 days, that X-Wever-Wallet-Proof must bind to the exact JSON arguments and route, and that the result carries an Ed25519 signed receipt. Those are precisely the operational facts an agent needs before invoking a paid endpoint.

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 purpose and sibling routing are front-loaded, which is good, but the body is a single dense run-on sentence that enumerates every report finding at length. The long checklist of 'every route with no path... every dropped task... every fallback or escalation to no one' repeats structure already implied earlier and makes the definition harder to scan than its content warrants.

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 contract, and it does: four named verdicts (no_road_back, failure_path_gaps, failure_path_unverified, road_back_defined), the report's finding categories, and the signed receipt. Payment mechanics, the wallet-proof header and the contract and human-page URLs are also supplied, leaving nothing material an agent needs to call this correctly.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning on top: it spells out the five outcomes (back to sender, named fallback, escalated, retried, dropped) that the on_refusal/on_failure/on_silence enums encode, clarifies that escalate_to_kind distinguishes named person, role, channel or agent, and explains that silence_after is a duration like 15 minutes and defined_at/first_failure_at are timestamps. The only gap is that it does not connect these semantics to the specific field names.

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 definition states a specific verb and resource: submit handoff routes with their failure paths and receive a signed report on refusal, failure and silence coverage. It also names the three nearest siblings and what each of them covers instead, so an agent can separate this tool from wever_breach-path-check, wever_incident-ownership-check and wever_approval-chain-check without opening any 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?

It gives explicit routing: work hitting a limit goes to wever_breach-path-check, an operator fallback when an agent is wrong or down goes to wever_incident-ownership-check, an unavailable approver goes to wever_approval-chain-check. That is clear when-to-use guidance with named alternatives. What is missing is a negative condition: it never says the tool should be skipped when, for example, routes have no failure concerns at all.

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