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

No annotations are provided, so the description carries the full burden, and it does disclose the non-obvious transformation (curated topic to CAEN codes). But it omits operational traits: it does not state the default result count, how results are ordered or paginated, or what happens with an unrecognized topic.

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?

Two sentences, front-loaded with the core purpose and followed by the optional-narrowing detail. The parenthetical topic examples are a bit list-heavy but earn their place by defining valid input. No wasted framing.

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 three-parameter, no-annotation, no-output-schema tool, the definition covers purpose, mechanism, and two of the parameters adequately. Since no output schema exists, return values need not be described, though the silent max_results default leaves a minor gap.

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 0%, so the description must compensate. It adds real meaning for 'topic' (a curated term with five examples) and 'county' (single-county narrowing), but 'max_results' is never mentioned, leaving one of three parameters entirely undocumented.

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 companies') and immediately differentiates from the sibling lookup_business by framing it as 'by what they do rather than by name.' It also explains the underlying mechanism (topic expands to CAEN activity codes), so an agent understands both what the tool returns and how it works.

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 'rather than by name' phrasing gives clear comparative context against the name-based lookups, and 'Optionally narrow the result to a single county' clarifies the county parameter's role. However, there is no explicit when-not-to-use guidance and no statement of which topics are valid beyond the five examples, leaving the boundary of acceptable input to inference.

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