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

Annotations already declare readOnly/idempotent/openWorld=false, and the description still adds material behavior: local-only execution, no registry hit, rate limiting per IP, no API key required, and a specific accuracy caveat that the final digit of new-format registration numbers (J2020001234400) is not verified. The explicit existence-check limitation prevents an agent from mistaking a pass for a validity guarantee.

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 sentences, no filler, front-loaded with the capability list before the limitations and the sibling handoff. The density is high but every clause (free, local-only, rate limit, last-digit caveat, alternative) carries actionable information.

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 five-parameter, zero-required validation utility with no output schema, the description covers capabilities, limits, cost, and rate behavior well. The remaining gap is that it never indicates what a response looks like (per-field pass/fail results?) or whether supplying several parameters yields combined or separate verdicts, which matters since there is no output schema to consult.

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 0%, so the description must carry the load; it partially does by mapping each check to a param (cui, iban, registrationNumber, name, invoice arithmetic with net/VAT/total/date/vatRates). However, it never states that all five parameters are optional and independently evaluable, which fields inside the nested invoice object are required, or the expected syntax for CUI/IBAN beyond the checksum concept.

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 the exact resource class and enumerates the concrete checks performed: CUI checksum, IBAN checksum plus Romanian bank derivation, old/new trade register format, company name normalization, and invoice arithmetic (total = net + VAT, Romanian VAT rates, future-date rejection). It also draws a hard boundary — 'no registry lookup' — that separates it from lookup_company and validate_extracted_company_data, so an agent can pick it without opening 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?

It states both the positive condition (offline format validation, works with no API key) and the exclusion ('Does not check that the company exists'), then routes the agent explicitly: 'For registry checks use validate_extracted_company_data.' That is a named alternative with a stated selection rule.

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