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

Beyond the readOnly/destructive annotations, the description discloses the decision vocabulary (APPROVE/REVIEW/BLOCK), the coverage-limitation disclosure, the source manifest, the 24-hour recheck time, the signed audit receipt, and the 'critical evidence failures are uncharged' billing policy. It also flags the 'where an open API exists' limitation on the register extract — all context the annotations do not carry.

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?

Two sentences with zero filler: the first front-loads purpose and components, the second covers outputs, timing, and billing. Every clause earns its place for a tool with this much behavioral surface.

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 6-parameter composite tool with an output schema present, the description covers the decision output, coverage limits, source manifest, recheck timing, audit receipt, and billing policy. The only notable omission is the semantics of require_register and registration_id, which an agent must infer from parameter names.

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?

With 0% schema description coverage, the description carries the burden and largely compensates: VIES maps to vat, IBAN validation to iban, sanctions-name screening to name, and the company-register extract to registration_id/require_register. The interplay of the optional parameters (require_register triggering the extract, registration_id's role) is left implicit, which is the main residual gap.

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 deliverable — 'Returns one APPROVE, REVIEW or BLOCK decision' — and enumerates the exact components (VIES identity, sanctions screening, IBAN validation, legal-name consistency, company-register extract). The composite 'dossier' framing distinguishes it from single-check siblings like validate_vat, validate_iban, and screen_sanctions_eu without needing to open their 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?

The opening phrase 'Professional procurement and onboarding dossier' gives clear context for when the tool applies — full onboarding/procurement vetting rather than a single check. It does not explicitly name alternatives or state exclusions, but the component list implicitly marks the individual-check siblings (validate_vat, validate_iban, screen_sanctions_eu) as the lighter-weight options.

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