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

Annotations already declare readOnlyHint and idempotentHint; the description adds meaningful behavior beyond that by defining the three output sections, the annual-dose content of focus, and the null-code behavior. It does not cover edge cases like invalid codes or year handling, but output schema and annotations carry the remaining burden.

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 one dense sentence that front-loads the main result ('focus') and packs the remaining output sections compactly. It is efficient and contains no filler, though a short list format would improve scannability.

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 retrieval tool with an output schema and two optional parameters, the description covers the default behavior, the hierarchy semantics, and the content of the returned records. Nothing an agent needs to decide whether to call it or understand its primary behavior 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 description coverage is 100%, so code and year are already documented with examples and default behavior. The description only restates the null-code behavior ('Ohne Kode') that the schema already explains, adding no new parameter-level semantics.

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 starts with 'Liefert' and names the ATC code, its defined daily dose, and associated ICD diagnoses, and it specifies the hierarchical result sections focus, parents, items. It also states the no-code fallback of returning anatomical main groups, which clearly distinguishes the behavior from the sibling atc_search.

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 usage: provide a code to get the code plus hierarchy fragments, or omit the code for top-level groups. However, it never says explicitly when to prefer atc_get over atc_search or other lookup siblings, so the guidance is implied rather than fully stated.

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