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

Annotations already cover the safety profile (readOnly, closed-world, non-destructive, non-idempotent) and the description still adds substantial new behavior: the analysis classification scheme (recovered / worked around / fatal), the verdict set, the Ed25519 signed receipt, and the explicit 'reads only the material in the call' guarantee. It also discloses commercial and auth behavior that annotations never carry: 0.10 USDC per call via x402, 10 free signed-wallet calls per rolling 30 days, and the X-Wever-Wallet-Proof header binding. It stops short of saying what happens on a malformed or contradictory trace.

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 in the first clause before payment, endpoints, and contract links. The paragraph is dense and packs a lot into one block; the payment/URL/contract tail could be separated or trimmed, but each item is operational information an agent needs (cost, auth header, route) rather than filler.

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-schema, no-output-schema tool, the description supplies the missing return-value picture (a report with an Ed25519 signed receipt and a verdict drawn from outcome_unexplained / fatal_failures / failures_absorbed / no_failures) plus the access and payment mechanics. Combined with 75% schema coverage and full annotations, an agent has enough to invoke it correctly without further documentation.

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 75%, so the schema does most of the work and the baseline of 3 applies. The description does add genuine semantic meaning for the important fields by tying required steps and fallback_for to the analysis ('which steps are required and which replace others'), and by explaining that the classification is tied to the recorded final outcome. It says nothing about the `job` or `label` parameters, which are left entirely to their schema descriptions.

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?

Opens with a specific verb+resource ('submit one job's execution trace') and enumerates exactly what the trace contains (steps, tool calls, failures, recoveries, required/replacement steps, final outcome). It also explicitly distinguishes itself from the closest sibling by naming it: 'per-job money is wever_job-cost-brief'.

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?

Clearly frames the task as post-hoc trace analysis and routes cost-related questions to wever_job-cost-brief. It does not spell out when a trace is *not* appropriate to submit (e.g. multi-job traces, or an incomplete trace that lacks final_outcome), so the exclusion side of the guidance is only implied.

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