Finn en statistikktabell

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

No annotations are provided, so the description carries the full behavioral disclosure burden. It explains Norwegian colloquial-term expansion, the escalation through exact/prefix/stem matching, and the meaning of the `strategi` field — including a warning that 'delvis' results should be read skeptically. This is rich, non-obvious behavior that an agent would otherwise not know.

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?

The description is dense but every sentence earns its place: scope, language behavior, match-strategy caveat, and routing to sibling tools. It is front-loaded with the core purpose and uses paragraph breaks to separate distinct ideas without padding.

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?

Given there is no output schema and no annotations, the description does a good job of setting expectations: it mentions the `strategi` result field, explains how to interpret match quality, and tells the agent how to retrieve data from the found table. It does not describe pagination or potential error cases, which are minor omissions for a search tool where the core usage is already clear.

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 only 33%, so the description must compensate. It does this for the key parameter `query` by giving two concrete examples ('konsumprisindeks', 'sykefravær') and explaining how the search interprets natural-language input. `limit` and `offset` are not described beyond their schema constraints, but their semantics are conventional and structurally annotated with defaults, min, and max.

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?

The description opens with a specific verb and resource: 'Søk i SSBs 3 898 tabeller' and names the exact searchable fields (title, description, dimension names). It also distinguishes itself from siblings by explicitly directing the agent to use `latest` or `data` with a table ID to get actual numbers.

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 description clearly tells the agent what to do after searching: 'Bruk `latest` eller `data` med tabell-IDen for å få selve tallene.' This gives a concrete usage boundary. It does not explicitly exclude all sibling tools like `table`, `status`, or `sync`, so it falls just short of a 5.

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