List Companies by Industry (NACE)

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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds valuable context beyond those: the SN2007 format incompatibility ('we do not store SN2007'), the data source (BRREG), and the daily refresh. These disclose meaningful quirks and data provenance, though it stops short of describing pagination or output structure.

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 compact and well-structured, with a one-sentence overview, a bolded critical warning, a sibling-tool pointer, and a usage tip. Every sentence earns its place; no filler or redundancy. The markdown formatting makes the key caveat visually prominent.

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?

Given 9 parameters, an output schema, and rich annotations, the description provides the essential context: primary use case, format caveat, data freshness, and a targeted filter tip. It doesn't detail pagination (cursor/limit) or all filter interactions, but those are partially covered by the schema and the output schema. The most critical gotcha (SN2007) is well emphasized.

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 only 44%, so the description must compensate. It adds a crucial format warning (trailing zero, SN2007 vs EU NACE) that is critical for correct use, and it highlights the stiftet_etter parameter for a specific query type. However, it doesn't elaborate on limit, cursor, or min/max_ansatte semantics, leaving some parameters under-explained.

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 opens with a specific verb+resource+scope: 'List Norwegian companies in a specific NACE industry code (or code prefix)', immediately clarifying what the tool does. It distinguishes itself from siblings like firmaradar_search_companies by focusing on NACE industry classification and from firmaradar_list_nace_codes by listing companies rather than codes.

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?

The description provides explicit when-to-use guidance: 'Useful for sector analysis' with a concrete example. It names an alternative tool ('call firmaradar_list_nace_codes first') when code uncertainty exists, and gives a specific filter tip ('Use stiftet_etter for newly-founded-company queries'). This exceeds the 4=clear context threshold.

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