opdater_profil

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds the crucial detail behind that risk: lists are replaced wholesale, so a partial list silently drops entries. It also clarifies that `aendringer` is a partial patch (only changed fields), which prevents an agent from sending a full overwrite. It does not cover permissions, validation failures, or what an unknown field key does, and the patch semantics sit slightly oddly against idempotentHint=false.

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?

Four short sentences, front-loaded with the core patch semantics before the examples and the usage trigger. Every sentence carries information; the only mild inefficiency is the parenthetical example payload, which is still illustrative rather than redundant.

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 destructive one-parameter write tool with an untyped nested payload and no output schema, the description covers the essential unknowns: what gets mutated, that it is a partial update, that lists overwrite, and where to find valid fields. Error behavior and return values remain unaddressed, but nothing critical for correct invocation 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 0% for a free-form nested object with additionalProperties=true, so the description carries the full burden and does so well: it gives two concrete payload examples, explains partial-update semantics, and routes the agent to vis_profil's `felter` for the valid key catalog. It stops short of documenting value types or validation for individual fields.

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?

"Ret husstandens profil" states a concrete verb (update) plus the resource (the household profile), and the reference to `felter` in vis_profil implicitly separates this write tool from the read-only sibling. It stops short of naming the alternative explicitly, so an agent must infer the read/write split.

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?

"Brug den, når husstanden siger, at noget skal huskes til fremover" gives a clear trigger condition tied to durable preferences. There is no when-not guidance (e.g. what to do for one-off basket changes versus persistent profile edits), but the read counterpart vis_profil is pointed to for discovering valid fields.

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