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

Adds substantial context beyond the annotations: closed-world behavior is spelled out ('no page fetch, no account access, no counterparty contact and no money movement'), plus a paid-call cost of 0.10 USDC on Base via x402, 10 free signed-wallet calls per rolling 30 days, and the required X-Wever-Wallet-Proof binding to exact JSON arguments and route. These are real operational constraints not derivable from readOnlyHint/openWorldHint. The only shortfall is that the signed-report structure is described in prose rather than tied to any output schema, so an agent still learns field names only by inferring from the verdict list.

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?

Dense but well front-loaded: capability, then output, then verdicts, then safety/scope, then pricing and auth, then references. Every sentence carries payload except the trailing human page URL, which is the one item that does not help an agent invoke the tool.

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 tool with no output schema, five parameters, a nested fields object, and a payment gate, the description covers what is computed, the full verdict enum, the receipt format, the safety envelope, and the billing/auth mechanics. Nothing an agent needs in order to call it correctly or predict the response is missing.

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%, and the schema already carries the field-precedence rule, format default, and 64 KB agreement cap, so the baseline is 3. The description adds value beyond that by explaining what the fields feed into — the current term rolled forward through automatic renewals, the notice deadline computed from the dates, the termination window — and by naming the four possible verdicts, which tells the agent what the output semantics of its input will be.

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?

States a specific verb and resource (submit agreement text and/or renewal fields plus current date, get a signed renewal report) and enumerates the report contents: renewal type, rolled-forward term, notice period and deadline, price-change terms, termination window, and flagged ambiguous language. It explicitly separates itself from the sibling wever_deadline-check ('Other document deadlines are...').

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?

Makes the input contract explicit ('submit agreement text, renewal fields or both, with the current date') and names the alternative tool for the adjacent use case, so an agent can route correctly without opening either schema. The boundary with wever_deadline-check is the exact ambiguity an agent would otherwise hit.

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