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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is largely pre-established. The description reinforces this ('no network request, fetch, money movement, message, sharing, configuration change or external write') and adds genuinely useful context the annotations do not carry: a paid x402 endpoint at 0.10 USDC per call, 10 free signed-wallet calls per rolling 30 days, and the requirement to bind X-Wever-Wallet-Proof to the exact JSON arguments and route. It also names the four possible verdicts and states that the return includes an Ed25519 signed receipt, which the annotations do not convey.

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 informational density is high, but the opening is a single sprawling sentence that lists inputs before stating the tool's function, so the description is not front-loaded. Grouping the input enumeration into a list or moving the purpose statement first would preserve all content and cut reading cost substantially.

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 five-parameter tool with no output schema, the definition covers what matters: the inputs, the field-by-field comparison behavior, the enumerated findings and their fixes, the four verdict values, the payment and auth mechanism, and links to the contract and human page. An agent has what it needs to decide whether to call it and how to shape the call.

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 description coverage is only 40%, so the description must compensate, and it does: it enumerates the agreement fields (parties, price, currency, method, network, payment and delivery due, order), the settlement fields (amount, currency, method, network, timing, order, escrow holder) and the per-step party ownership. It also explains the semantic role of steps, notably flagging 'steps after a step the list lacks' and 'every step no party owns', which clarifies the `after` and `owner` fields beyond the terse 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?

The description names a specific verb ('submit one agreed deal and its settlement') and resource, and states that 'the signed report reads the settlement against the agreement field by field and step by step', which is clearly distinct from the named siblings. It would score 5, but the actual purpose statement is buried mid-paragraph after a long enumeration of input fields, so the reader must parse a dense block before learning what the tool does.

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 explicitly routes three alternatives: expected settlements against transfers go to wever_settlement-reconciliation-check, a payment instruction to wever_payment-instruction-check, and a settlement claim against chain evidence to wever_settlement-proof-check. The condition that selects each sibling is stated outright, leaving nothing to inference.

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