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

Well beyond the readOnly/openWorld annotations, the description discloses pricing (2 credits, base lookup plus section), the ordering caveat that a late or corrected filing can precede a newer year, the semantics of revideret and revisorbistand, and the no-cost tier refusal. It does not say how many rows or what an empty result looks like, so it stops just short of a 5.

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 what the tool returns, then costs and alternatives, so the important content comes first. It is a dense single paragraph and the sentence explaining aarsrapport/offentliggjort is close to schema-detail territory, but the Danish term glosses earn most of the length.

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?

No output schema exists, yet the description explains the returned fields, per-year fiscal year identification, auditor fields, the source link, and the publication date — everything needed to interpret a response. It also covers the cost and refusal cases, leaving no significant gap for a one-parameter, read-only tool.

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% and the pattern is documented, so the baseline applies; the description still adds value by explaining the CVR is the lookup key and that a name must be resolved through search_companies first. That is useful routing context the schema does not carry.

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 resource (annual accounts for one Danish company) and enumerates the actual contents: revenue, EBIT, EBITDA, profit, equity, balance sheet and key ratios, bounded to four filed years. This is clearly distinguishable from siblings like get_business_profile or get_credit_risk without opening any schema.

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 rules: use search_companies first when you only have a name, and use get_company with `sections` instead when the user needs the profile or more than one section because it is cheaper and faster. It also names the failure mode (tier_restricted, refused at no cost) and how to report it, which is usage guidance at its most concrete.

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