UDIR: hva skal eleven kunne i dette faget på dette trinnet?

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

With no annotations, the description carries the full burden. It discloses the content returned (competency goals plus assessment text) and cites source and license, but it does not describe response format, error behavior, or whether results are returned as text or structured data.

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 core semantics and usage rule are front-loaded into a compact first paragraph, and the source/license note is brief. No filler, though the misleading year-range shorthand shows the text was not fully aligned with the schema.

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 simple two-parameter lookup, the description covers parameters, output content, and one key exclusion, and it gives provenance. It is incomplete in two ways: it does not describe the response shape (no output schema exists), and the 1–13 instruction is inconsistent with the schema, forcing the agent to reconcile conflicting guidance.

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?

The schema already documents both parameters completely, so the baseline is 3. The description's contribution is weakened by the 'årstrinn 1–13' shorthand, which conflicts with the schema's valid values of 1–10 or vg1/vg2/vg3 and could lead an agent to submit invalid integers. The fag examples merely repeat schema information.

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 clearly states the deliverable: competency goals from LK20 for one subject at one year level, plus the underveisvurdering text. It also distinguishes itself from school-specific lookups by saying it is not about a particular school.

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?

It gives an explicit use condition: choose this tool when the question is about what is expected at a year level, not about a specific school. It does not name sibling curriculum tools such as udir_laereplan, so the routing guidance is directional rather than exhaustive.

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