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

Annotations already mark the tool as readOnly, idempotent, and not open-world, so the safety profile is clear. The description adds valuable behavioral detail beyond annotations by disclosing the response sections ('focus', 'parents', 'items') and the special behavior when no code is supplied. It does not describe invalid-code handling, but this is minor for a read-only lookup.

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 two well-structured sentences with no filler. The first sentence front-loads the key output behavior, and the second efficiently explains the optional-code case. Every sentence adds necessary information.

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 read-only tool with two optional parameters, complete schema documentation, an explicit output schema, and strong readOnly/idempotent annotations, the description covers what an agent needs to invoke it correctly. It explains optional invocation and the structure of results without over-explaining.

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 both 'code' and 'year' already documented in the input schema. The description reinforces that omitting 'code' returns main groups, but it does not add meaningful information about 'year' or parameter formatting beyond what the schema provides. Baseline 3 is appropriate.

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 names the concrete verb 'Liefert' and the resource 'ATC-Kode', and clearly specifies what is returned in 'focus', 'parents', and 'items'. It also distinguishes itself from the sibling 'atc_search' by describing hierarchical retrieval with parent/child structure rather than search, and by explaining the no-code root-group behavior.

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 gives clear usage context: pass a code to get focus/parents/items, or omit the code to get anatomical main groups. It does not explicitly mention when to prefer 'atc_search' instead, but for this retrieval-style tool the conditional behavior is strong enough guidance.

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