run_at_companies

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

With no annotations, the description carries the full burden, and it partly meets it: it enumerates the returned fields (name, status, legal form, address, previous names, paid extracts) and discloses the cost model ('Flat 5 points per successful run'). It says nothing about authentication, error behavior for an invalid FN, or rate limits, so the behavioral picture is incomplete.

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?

One dense, front-loaded sentence covering identifier, source, and returned fields, followed by a short pricing note. Nothing is padded. The return-field list is slightly long but is the main value-add given there is no output schema.

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 one-parameter lookup with no output schema and no annotations, the description compensates well by enumerating the response fields and stating the point cost. It is essentially complete for correct invocation; only failure/permission behavior is left unaddressed.

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% and the single 'company' parameter already documents both the FN format and the example token, so the description cannot add much. Its 'registration number (FN) or registry URL' phrasing restates the schema rather than extending it. Baseline 3 is appropriate.

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 (Get one company), the exact resource (Austria registry / Firmenbuch), and the accepted identifiers (FN or registry URL), plus an enumerated field list. It clearly reads as a single-entity lookup, which implicitly separates it from the broad family of company tools. The one gap versus a 5 is that the obvious sibling run_at_companies_search is never named, so the routing distinction is left to inference.

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?

Usage is implied by the input contract: an agent should reach for this when it already holds an FN or registry URL, and use a search variant when it only has a name. However, no alternative is named and no when-not condition is given, so the guidance is inferred rather than stated.

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