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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds material context beyond that: the checks run in parallel, any subset of name/email/phone/vat suffices, the exact verdict vocabulary, and the cost/free-tier mechanics that materially affect whether an agent should call this repeatedly.

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?

A single dense paragraph that front-loads the trigger, then scope, then the verdict vocabulary, then cost. Every clause carries information, but the run-on construction and the inline payment details make it harder to scan than a two- or three-sentence split would be.

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 12-parameter, no-output-schema, paid read tool, the description covers the essentials: what it checks, what verdicts come back, and what it costs. It does not explain how partial inputs change coverage (e.g. name-only vs name+VAT), or what 'incomplete' means operationally, which is the main remaining gap.

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 12 parameters and only 50% schema description coverage, the description must compensate, and it does partially: it names name, email, phone and vat as the inputs and states that any subset is acceptable, which is the key semantic an agent needs. However, it never mentions kvk, pep, type, company, country, birth_year or company_country, and 'send any of name, email, phone, vat' arguably understates the accepted input set.

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 a specific verb-and-resource bundle: screens a name against EU/UN/UK/US sanctions and PEP, verifies email and phone, and checks an EU VAT number in VIES. It explicitly bounds the scope ('not a company deep-dive') and enumerates the four verdicts, so an agent can distinguish it from company_lookup, company_dossier, eu_sanctions_screen, email_verify and eu_vat_check without opening a 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?

Opens with the trigger condition ('when onboarding a new customer, seller or business') and adds a negative condition ('not a company deep-dive'), which routes the agent away from the deep-dive siblings. It also spells out the payment paths (x402 USDC, Factline credits, five free calls per day), which is usage guidance as much as pricing.

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