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

Annotations cover the safety profile (readOnly, idempotent, openWorld), and the description adds substantial behavior beyond them: a two-call x402 payment handshake, per-section parallelism with independent timeout guards, graceful degradation (a failing section returns status "unavailable" rather than failing the whole call), and per-section status/sources output. It also clarifies the server never holds a wallet, which is important for a paid tool.

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?

It is long but dense and front-loads the paid/pricing signal, then the section list, then failure behavior, then the payment handshake. Minor redundancy: the $0.05 price and "paid via x402" are stated three times, and the wallet-ownership point is repeated.

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 an 8-parameter composite tool with no output schema, the description covers the essentials: what runs and when, partial-failure semantics, the two-step payment protocol including the exact header shape to echo back, and cost. Nothing an agent needs to invoke it correctly 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 description coverage is 100%, so the schema already documents mutual exclusivity of name/ticker/lei/cik and the optionality of email/domain/wallet; baseline would be 3. The description adds routing semantics the schema cannot express — that any combination of identity/domain/wallet/email is allowed and that only sections backed by supplied arguments execute — which is genuine added value.

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 composite resource (a merged KYB report) and enumerates exactly which sub-reports it runs (company_lookup, sanctions_screen, domain_intel, wallet_profile, email_validate), each corresponding to a sibling tool. An agent can immediately distinguish this aggregator from the individual section tools without opening any 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 states the use case (compliance/onboarding) and the triggering condition clearly: supply at least one of name/ticker/lei/cik/domain/wallet/email, and only the implied sections run. It also frames the alternative economically (bought separately up to $0.064 vs flat $0.05), but never explicitly names a sibling like company_lookup or wallet_profile as the thing to use when you only need one section.

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