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

Goes well beyond the readOnly/openWorld annotations by disclosing the cost (1 credit), revealing that this call performs the base company lookup internally, and warning that employee figures come from a register interval that can lag reality by months. The data-freshness caveat and cost/overlap semantics are exactly the kind of context annotations cannot carry.

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?

Front-loaded with the output contents, then cost, then the sibling comparison — a sensible ordering. It is dense and somewhat run-on in the middle (employee counts, intervals, FTEs, tegningsregel in one clause), so it is efficient rather than elegant.

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?

There is no output schema, so the description carries the return-value burden and discharges it by naming every returned field group, plus cost, freshness caveat, and when to prefer get_company. An agent has everything needed to call it and to anticipate the response.

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 single cvr param is already documented with pattern and format), so the baseline would be 3. The description adds real value on top by specifying how to obtain the identifier — CVR lookup only, route to search_companies when you merely have a name — which is not in the schema.

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 plain-language statement of the operation — what one Danish company does and how big it is — then enumerates the exact fields returned (industry code, secondary industries, employee interval, FTEs, capital, tegningsregel, purpose). It is clearly distinct from siblings like get_contact_details, get_ownership, or get_company.

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 explicit routing for the two obvious forks: use search_companies first when you only have a name, and call get_company instead when the user wants more than this slice, since it costs the same. That is when-to-use, when-not, and the named alternative all in one place.

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