Company registry facts

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

Annotations already mark readOnly/openWorld/idempotent/non-destructive, and the description adds substantial behavior beyond them: the 24 h cache window, the full failure-mode list (NOT_FOUND, SCOPE_INSUFFICIENT needing read:brreg, UPSTREAM_TIMEOUT, VALIDATION_FAILED), the per-call cost and INSUFFICIENT_CREDITS behavior, the sandbox testing path, and the privacy guarantee ('never personal identifiers'). This is far more than the annotations alone provide.

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 description is long but dense — every sentence carries distinct operational information: purpose, fields, cache, selection rule, pairing, failure modes, alternatives, sandbox credentials, cost, and docs URL. It is front-loaded with the core purpose and flows logically. For a paid tool with many siblings and testing quirks, none of this is 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 single-parameter, fully-schema-documented, output-schema-having read-only tool, this is complete. The description covers when to use it, when not to, failure modes, auth scope, caching, cost/credi t behavior, and the sandbox route — nothing an agent needs to cal it correctly is missing. The output schema relieves the description of explaining return values, and the schema covers the parameter.

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%: the schema already documents the 9-digit pattern, MOD-11 validation, and VALIDATION_FAILED behavior. The description adds value beyond this by identifying the parameter as the Brønnøysund registry identifier for Norwegian organisations and, more operationally, pointing to GET /api/v1/sandbox/fixtures as the source of valid test org numbers. It doesn't fully compensate beyond the schema, but the sandbox sourcing tip is a genuine increment.

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?

Opens with a specific verb+resource+scope: 'Retrieve the structured Brønnøysund identity slice for a Norwegian organisation by its 9-digit organisasjonsnummer', then enumerates the exact returned fields (legal name, organisasjonsform, NACE codes, addresses, dates, signaturrett/prokura codes). It explicitly names the siblings it is not — get_company_summary and get_company_profile — removing all ambiguity against the 24-tool sibling list.

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 an explicit selection rule: 'Choose this for the identity slice ONLY, without the compliance verdict', tells the agent what to pair it with ('pair with get_company_obligations or get_company_deadlines for the regulatory layer'), and names the precise alternatives for other needs ('for a compliance verdict, use get_company_summary instead; for the plain registry profile with NACE descriptions, use get_company_profile instead'). Nothing 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.