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

Annotations already declare readOnlyHint=true and openWorldHint=false; the description reinforces this with an explicit enumeration of what is not done (no network request, fetch, money movement, message, sharing, configuration change or external write). It also discloses cost (0.10 USDC on Base via x402 exact, 10 free signed-wallet calls per rolling 30 days) and the wallet-proof binding requirement, which annotations cannot convey. It does not address the non-idempotent billing implication beyond per-call pricing, but there is no contradiction.

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 and the sibling exclusion are front-loaded, followed by output behavior, safety scope, and billing. The paragraph is dense but every block carries information an agent needs (cost, auth binding, return shape). The contract path and human page URLs are the least essential items and add slight tail weight.

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?

With no output schema, the description carries the return-value burden and does so: it names the verdict values (stale_answers, touched_but_current, none_touched), the per-answer flagging with quoted superseded basis and stale/unaffected reason, and the Ed25519 signed receipt. Combined with the disclosed cost, auth header, and route, nothing material is missing for correct invocation.

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 baseline would be 3, but the description adds real meaning: it maps the answers array to question, answer time, and 'its basis or source where recorded' (clarifying basis is optional), and it explains the either/or shape of change as old/new section text versus a stated change description. It does not explain the label, effective_date, or the 500-answer / 100-section limits beyond the schema.

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: submit prior answers plus a superseding change, and receive a signed report flagging answers whose basis the change touches. It also names the sibling it is not (wever_terms-change-check for comparing two full policy versions), so an agent can distinguish it from adjacent 'change-check' tools without opening a 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 specifies the required inputs (prior answers with question/answer/time/basis and the change as either old+new sections or a stated description) and explicitly routes the policy-diff case to wever_terms-change-check. That gives both a when-to-use condition and an exclusion with a named alternative.

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