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

Goes well beyond the annotations by disclosing cost and payment mechanics (0.10 USDC per call on Base via x402 exact, plus 10 signed-wallet free calls per rolling 30 days), an authentication binding requirement (X-Wever-Wallet-Proof bound to the exact JSON arguments and route), and the output artifact (a report with an Ed25519 signed receipt). The 'reads only the material in the call' line also resolves the apparent tension between the submit verb and readOnlyHint=true by clarifying no external state is touched.

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?

Front-loaded with the core action and verdict, then validation scope, then cost/auth/return details, so an agent can stop reading early. Sentences are long and clause-dense, and the trailing contract/human-page links sit at the end where they belong, but the validation clause reads as a run-on list that could be tightened.

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 deeply nested 3-parameter tool with no output schema, it covers the essentials an agent needs: what goes in, what is validated, what verdict comes back, that a signed receipt accompanies the report, and the payment/auth overhead. The only gap is that report structure and error behavior are left to the referenced contract rather than described here.

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 already 100%, so the baseline is 3, but the description adds interpretive value by mapping packet sections to their purpose (legal or agent identity, contact, wallet or bank payment route, terms acceptance, compliance fields) and by listing what each is validated against: email/phone/website formats, wallet or IBAN/SWIFT-BIC/routing formats, account holder versus legal name, terms version and date, compliance dates and open statuses. It does not explain the optional top-level label or the free-form compliance key naming rules, leaving those entirely to 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?

States a specific verb and resource: submit a counterparty onboarding packet and have it checked for completeness and internal consistency, producing a verdict of complete, incomplete or inconsistent. It also names the sibling it is not (wever_counterparty-brief) and gives the route POST /api/counterparty-onboarding-check, so an agent can distinguish it from the many other *-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?

Explicitly routes research on the counterparty itself to wever_counterparty-brief, which is a clear alternative-selection rule. It also scopes what the tool does not do (no page fetch, no account access, no counterparty contact, no money movement). It stops short of stating when NOT to run a check at all (e.g. packet prerequisites or failure handling), so it is clear context rather than exhaustive when/when-not guidance.

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