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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, and the description still adds substantial behavior: concurrent execution across registers, the specific data sources queried, the enumerated verdict values (APPROVED/FLAGGED_FOR_REVIEW/REJECTED), the audit trail, single round-trip semantics, and cost/rate-limit terms ($0.010/call after 5 free/day). Pricing and quota are exactly the kind of operational context annotations cannot express.

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?

Three front-loaded sentences: capability, sources, then output and cost. Nearly every clause carries information an agent needs. The trailing parenthetical pricing note is useful but slightly sales-toned, keeping it just below top marks.

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?

An output schema exists, so return structure need not be explained, and the description nonetheless surfaces the verdict enum and audit-trail guarantee. Annotations cover the safety profile and the description covers cost and concurrency. The only real gap is guidance on what an agent should do with a FLAGGED_FOR_REVIEW outcome or how latency scales with more identifiers.

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 every one of the five parameters (name, domain, country, vatNumber, registrationNumber) is already documented with examples in the schema. The description adds no guidance on how the optional identifiers affect match confidence or verdicts, so it earns the baseline 3 and nothing more.

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+resource ('Composite autonomous KYB vendor due diligence tool') and enumerates the exact sub-tasks performed: corporate identity resolution across global registers, VIES VAT validation, and OFAC/EU/UN sanctions screening. The word 'Composite' plus 'in a single round trip' distinguishes it from the granular siblings resolve_entity, verify_eu_vat, and screen_sanctions without the agent needing to open 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?

The description gives clear selection context: this is the all-in-one path that folds three sibling capabilities into one call, which implicitly tells the agent when to prefer it over calling the individual tools. It stops short of explicit exclusions — it never says to use batch_resolve for multiple vendors or resolve_entity alone when only identity is needed — so it lands at 4 rather than 5.

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