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

Goes well beyond the readOnly/idempotent/openWorld annotations by disclosing the credit cost model (2 base, +5 for legalRepresentative, +1 for invoice), the billing exemptions (errors, ANAF unreachable), determinism of the confidence score, and the fact that legalRepresentative is never stored. These are exactly the operational facts an agent can't get from annotations.

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 and information-dense, but the sentence "Checked against public sources (ANAF, ONRC) and checksums" repeats the opening claim almost verbatim, and the pay/review warning appears twice ("Use before saving to an ERP or paying" and "Always review before paying"). Trimming would gain readability without losing content.

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?

No output schema exists, and the description fully covers the return shape: a verdict, the registered value per field, optional invoice arithmetic results, and a deterministic confidence score with pass/review/reject. Combined with the cost and caveat disclosures, an agent has everything needed to call it and interpret results correctly.

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 schema coverage at only 33% across three nested-parameter top-level keys, the description compensates by naming what each payload area is checked for (CUI, name, registration number, VAT status, company status, address, IBAN, legal representative) and flagging invoice arithmetic checks and the +5 credit cost of legalRepresentative. asOfDate semantics and the invoice sub-fields are left to the schema, keeping this short of a 5.

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?

Names a specific verb (checks/validates) and a specific resource (extracted Romanian company data) against named authoritative sources (ANAF, ONRC) plus checksums. It also enumerates the returned fields and verdict categories, so an agent can distinguish it from lookup_company (raw lookup) without opening the 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?

Gives explicit usage context ("Use before saving to an ERP or paying") and explicit exclusions ("Not a KYC/AML check", structurally valid IBAN does not prove ownership, always review before paying). The only gap is that it never names the sibling alternative (e.g. lookup_company) that an agent should use instead when starting from scratch rather than from extracted data.

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