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

Annotations only cover read-only/non-destructive/open-world, but the description adds cost (1 credit), the underlying endpoint, country-resolution behavior, and the full error contract (400 for VAT-less registers, 404 for no match, 409 with candidates for ambiguous numbers). It also explains meta.resolved_by and its enumerated values, which is real behavioral detail an agent cannot get elsewhere.

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?

The core capability, cost and endpoint are front-loaded, and every sentence carries operational meaning. It reads as one dense run-on paragraph of shorthand, so it is efficient but not maximally scannable.

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?

With no output schema, the description still characterizes the response ('answered like company_detail with the same include', plus meta.resolved_by), and it covers all three identifier modes and their failure modes. An agent has everything needed to call it 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?

Schema coverage is 100%, so the baseline is 3, but the description goes beyond it by explaining how VAT prefixes imply country (EL is Greece, XI Northern Ireland, CHE Switzerland) and when country is mandatory. The include parameter is only loosely described as 'as on company_detail', which keeps it from 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?

States a specific verb and resource ('Find ONE company from an identifier') and scopes it further with the endpoint, cost (1 credit) and the promise that it answers like company_detail. That cleanly separates it from name-based siblings such as companies_search and from vat_validate.

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 per-type usage rules: vat needs a prefixed number or a country, lei uses GLEIF links, company_number requires country, and countries with no VAT register return 400. It never explicitly names an alternative tool (e.g. 'use companies_search for names'), so it falls short of the when/when-not/alternatives bar.

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