NGU: grunnforhold i et punkt

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

There are no annotations, so the description carries the full behavioral burden. It does disclose a useful behavior: the response includes a 'mangler' field for parts that could not be fetched. It also names the source and license. However, it does not describe read-only status, response wrapping, rate limits, or coordinate-system expectations, which remain unspecified.

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 front-loaded with the tool's purpose and content, followed by use cases, error behavior, the sibling alternative, and source/licensing. It is slightly longer than strictly necessary, but every sentence contributes practical information for invocation.

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 3-parameter lookup tool with no output schema, the description covers purpose, domain, common use cases, partial-failure behavior, and the key sibling alternative. It is missing precise coordinate-parameter semantics and any indication of response shape, leaving the agent to guess about lat/lon formatting and default radius behavior.

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 only 33%, so the description must compensate for the undocumented lat and lon parameters. It refers vaguely to 'dette koordinatet' and 'i nærheten', but never defines coordinate order, CRS, value ranges, or how radius_m behaves beyond the schema's own brief description. This is not enough to fill the coverage gap.

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 clear question-resource mapping: 'Hva består grunnen av på dette koordinatet' and then enumerates the concrete data categories it returns (radon, løsmassetype, marin grense, wells). It also explicitly distinguishes itself from ogc_punkt for NGU's other 27 datasets, so an agent can tell it apart from related siblings.

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 explicitly gives usage contexts ('Bruk denne ved boligkjøp, tomtevurdering, graving eller planlegging av bergvarme') and names the alternative for other NGU datasets ('bruk ogc_punkt'). This is exactly the when-to-use and when-not-to-use guidance the dimension asks for.

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