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

Beyond the annotations (already readOnly/openWorld=false), the description discloses that the call performs no network request, fetch, money movement, message, sharing or external write, that it costs 0.10 USDC per call on Base via x402 exact with 10 signed-wallet free calls per rolling 30 days, and that a wallet proof must be bound to the exact JSON arguments and route. That is meaningful operational detail no annotation conveys, and it is consistent with readOnlyHint=true rather than contradicting it.

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 input requirement, then the verdicts, then sibling routing, then cost/contract. The problem is packaging: it is a single run-on paragraph with long parenthetical field lists, so pricing, auth binding and routing are buried mid-sentence instead of structured. Every clause earns its place content-wise, but readability suffers.

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 correctly compensates by naming all five verdicts (pays_as_itself, not_delegated, delegation_gaps, identity_unverified, properly_delegated) and stating the report is Ed25519-signed, and it supplies the endpoint, contract path, human page and payment terms. The remaining gap is behavior when no delegation is supplied, which is significant for a nested two-object comparison tool.

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 only 33%, so the description must compensate, and it largely does: it enumerates the receipt fields (named buyer identity and its kind, party paid for, acting agent, merchant, category, amount, time, credential) and the delegation fields (principal, agent, merchants, categories, max amount, expiry, revocation method and time). What it does not add is semantics for the enums (credential values like agent_wallet vs business_wallet vs shared_business_key, revocation 'none') or the accepted amount/expires formats, which remain undocumented in both places.

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 a purchase receipt plus the delegation behind it and receive a signed report on whether the receipt's buyer identity is the delegating principal and the acting agent is the delegated one. It also explicitly separates itself from three near-name siblings (wever_delegated-authority for issuing, wever_delegation-check for a delegation's own terms, wever_agent-identity-check for the agent record), so an agent can route without opening 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 names the alternatives and what each covers, which effectively tells the caller when not to use this tool. However it never says what happens if the optional delegation object is omitted (delegation has required: []), which is the main usage ambiguity for a tool whose whole point is comparing a receipt against a delegation; the caller is left to infer whether omission triggers identity_unverified or an error.

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