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

Annotations (readOnlyHint, openWorldHint) cover the safety profile and are not contradicted — this is a read-only lookup. The description adds genuinely useful behavior beyond the annotations: the tool is paid, it returns a uniform JSON schema across countries, and coverage is conditional ('Denmark/UK when enabled; elsewhere via GLEIF'). These are behavioral traits an agent cannot infer from annotations alone.

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 core action and unified-schema promise, then the coverage list and cost. Every clause earns its place: the registry list disambiguates from country-specific siblings, the 'when enabled' clause sets coverage expectations, and the price is essential pre-invocation information. It is one long sentence with nested parentheses, so slightly harder to parse than ideal, but there is zero filler.

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 4-parameter tool with a rich schema, an output schema, and safety annotations, the description is nearly complete: geographic scope, data content, output uniformity, conditional coverage, and cost are all covered. The main gap is that France and Germany — countries with dedicated sibling profile tools — are not explicitly addressed, so an agent must infer they are out of scope. Since an output schema exists, return-value documentation is not the description's job.

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 the baseline is 3: pays, id, api_key, and x_payment are already well documented in the schema, including x402/api_key precedence and insufficient-balance error behavior. The description adds modest value by linking the registry acronyms (KBO/BCE, ARES, Zefix) to the concept of 'national register ID', which grounds the id parameter, but it contributes no new formats or constraints beyond the schema.

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 precise action ('registry lookup') and resource ('unified European company profile'), scoped by 'country and national register ID', and enumerates the exact registries covered (KBO/BCE, ARES, RPO, PRH, KRS, Zefix, GLEIF). This clearly differentiates it from siblings like get_french_company_profile or get_belgian_company_filing. The 'same JSON schema for every country' clause further specifies what the returned profile contains.

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 clear applicability context: an explicit country/registry list, a conditional ('Denmark/UK when enabled'), and a fallback route ('elsewhere via GLEIF (LEI)'), plus a cost signal ($0.01 via x402) that an agent needs before invoking. It never names alternatives or exclusions (e.g., 'for France, use get_french_company_profile'), so routing between 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.