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

Going well beyond the readOnly/openWorld annotations, it states that it reads only the material supplied ('no network request, fetch, money movement... external write'), that it returns an Ed25519 signed receipt, and that it is a paid endpoint with a specific price, rail and free-call allowance. It also discloses the auth requirement (X-Wever-Wallet-Proof bound to the exact JSON arguments and tool route), which is behaviour an agent cannot infer from annotations or schema.

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 core is front-loaded correctly, but the opening sentence is a 60-word run-on and the closing block stacks pricing, auth binding, contract URL and human page into the same paragraph as the verdict list. The long enumeration of non-actions ('no network request, fetch, money movement, message, sharing, configuration change or external write') is heavier than needed given the readOnly annotation.

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, paid, third-party-call tool with no output schema, the description covers the report contents (per-permission enforcement classification plus fixes), the verdict vocabulary and the receipt format, which is what an agent needs to interpret results. Error behaviour and the meaning of the optional label field are the only notable omissions.

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?

At 67% schema coverage, the description compensates by explaining what each permission entry must contain: every layer where it is enforced or stated (gateway, policy engine, platform, credential scope, tool code, database, system prompt, tool description, conversation), the fail behaviour, and whether a tool lets the model alter the layer. That gives semantic meaning to the enforced_at, fails and model_can_change fields beyond their enum listings.

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 precise action ('submit a system's permission design') and a precise output ('signed report names every permission enforced outside the model... every outside enforcement that fails open'). It also explicitly demarcates the sibling tools wever_gateway-coverage-check, wever_gateway-rules-check and wever_deterministic-core-check, so an agent can discriminate without opening their schemas.

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 routes the agent away from three named sibling tools and lists the four possible verdicts, which tells the caller what outcome to expect. What's missing is an explicit positive trigger ('use this when you have a permission inventory and need to know which layers actually enforce it') and any prerequisites or exclusions beyond the sibling contrast.

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