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

Annotations already declare read-only, idempotent, open-world and non-destructive, and the description still adds real context on top: the per-call price (0.05 USDC / 25 credits), the free-tier allowance of five paid calls per day with no key, and the four possible verdict outcomes. Pricing and the payment-vs-key path are exactly the operational facts an agent cannot get from structured fields.

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 use case, then coverage, then verdict, then input and pricing — a sensible order. The long mid-sentence enumeration of ten country codes is dense but each clause carries distinct information. Slightly overpacked for a single breath, but nothing is redundant.

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 still tells the agent what comes back (a single verdict from four values). Zero required parameters over seven inputs is handled by 'name or id, best with country'. Payment, auth and free-tier paths are all covered, leaving no material gap for correct invocation.

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 100%, so the baseline is 3, but the description adds a non-obvious heuristic the schema does not: 'name or id, best with country', signaling the call works with a name alone and that country improves matching. It also mentions kvk as the bankruptcy trigger, reinforcing the schema. Not a 5 because vat and domain are not elaborated beyond their schema descriptions.

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 specific verbs (finds, screens, checks, flags) and a precise resource scope: a European company across 10 named registers plus sanctions/PEP/VAT/Peppol/bankruptcy checks, collapsing into one verdict. That is far more than a restatement of the name. It stops short of 5 because it never names the sibling it replaces (company_dossier, kyc_check, eu_sanctions_screen), leaving the agent to infer differentiation from the enumerated coverage.

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?

Opens with an explicit trigger: 'Use before onboarding, paying or contracting a European company', which is a concrete decision context. It gives no exclusion or when-not guidance, and does not point at alternatives for cheaper narrower checks, so it falls short of the top band.

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