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

Annotations already mark it read-only and non-destructive, but the description adds real behavioral context beyond them: a 2-credit cost, the tier-restriction refusal path with the exact error code, the zero-cost nature of that refusal, and the score's nature as an algorithmic rating. These are exactly the operational details 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?

Three sentences, front-loaded with what the value is, then cost and alternatives, then the failure mode. Every sentence carries distinct decision-relevant information with no waste.

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 single-parameter read tool with no output schema, the description covers what is returned (score plus underlying warnings/flags), what it costs, when to prefer an alternative, and how a restricted plan manifests. Nothing needed to invoke it correctly is missing.

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 sole parameter is already documented as an 8-digit CVR, so the schema does the heavy lifting. The description adds a useful lookup hint tying the parameter to the name-to-CVR workflow via search_companies, giving marginal meaning beyond 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?

States a precise verb+resource: returns the SI-score (0-10) risk rating for one Danish company, including the warnings and critical flags behind it. It explicitly scopes the entity types (limited companies and foundations) and clarifies this is an algorithmic score, not a credit rating — a distinction an agent could otherwise get wrong when compared to get_company or get_financials.

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 the routing rule (use search_companies first when you only have a name) and an explicit alternative with its selection condition: one get_company call with `sections` is cheaper and faster when the user also needs the profile or multiple sections. It also tells the agent how to handle the tier_restricted outcome rather than reporting data as absent.

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