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

Annotations already cover the safety profile (readOnly, openWorld, non-destructive), so the bar is lower. The description earns credit by adding non-obvious behavior: billing semantics ('not charged when the site cannot be tied to one company'), that LEI lookups also return parent entities, and that name lookups return a short candidate list.

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?

Purpose is front-loaded, followed by coverage and then a compact 'Use when' clause; no sentence is wasted. The register list is dense but informative rather than padding.

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 six-parameter open-world lookup with rich schema descriptions and no output schema, the definition covers scope, country-specific register behavior (CZ/NO/GB/US native vs. GLEIF fallback), and cost nuance. It could still say more about multi-country resolution or failure modes, but nothing required to invoke it correctly is missing.

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 100%, so each parameter is already fully documented with format constraints (patterns, max lengths, exactly-one-of rule). The description only restates the input modes collectively ('by registration number, name and country, VAT number, LEI or website') without adding syntax or precedence detail, so the baseline 3 applies.

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 concrete verb+resource ('Business registry lookup: company identity and legal entity enrichment as structured JSON') and enumerates the exact register coverage (CZ, NO, GB, FR, FI, US SEC, LEI). It never explicitly distinguishes itself from the 'company-de' sibling, so an agent must infer that Germany lives elsewhere — a real but minor gap.

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 gives one qualifying condition, 'Use when: you need the official identity of one company,' which implies the single-entity scope. It names no alternatives (company-de, due-diligence, verify, sanctions) and no when-not case, so routing between the many siblings is left to inference.

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