UDIR: slå opp én skole

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

With no annotations present, the description must shoulder behavioral disclosure; it indicates a read-only fetch ('Henter') and adds provenance/license, but says nothing about response shape, unknown-id errors, pagination, rate limits, or any side effects. This fails to fully disclose operational behavior beyond the basic lookup action.

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?

Two short sentences, front-loaded with the core purpose followed by source/license; zero fluff. The essential operation is visible in the first seconds without parsing.

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?

The tool is simple (one param, no enums, no nested objects), so the description does not need heavy structure; but since there is no output schema or annotations, the vague 'detaljer' leaves the agent unsure what fields to expect. The Norwegian-context and source/license provide useful domain context, but error and return contract remain unspecified.

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%, with the lone parameter id described as 'NSR-id fra udir_skoler'. The description merely echoes this by saying 'via NSR-id', adding no new semantic detail such as format, range, or example. Thus the baseline 3 applies.

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 the explicit action 'Henter detaljer for én enhet i skoleregisteret via NSR-id' – a specific verb (fetch), a concrete resource (one school entity), and the key identifier (NSR-id). It is clearly distinguishable from the sibling udir_skoler (list/search) and from skolverket_skole (Swedish counterpart). The addition of source and license further pins the domain.

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 implies the tool is for a single-school lookup keyed by NSR-id, and the title says 'slå opp én skole'. However, it does not explicitly direct when to use it over udir_skoler or state that NSR-id must first be obtained from udir_skoler (that dependency is only in the schema's parameter description). There are no exclusions or alternative routing hints in the description text.

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