ATC Class Members

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

Annotations already declare readOnlyHint and idempotentHint, but the description adds valuable context: each member includes a substance-level 7-char ATC code via source_atc_code for disambiguation at levels 1-4, and the RxNorm catalog is US-centric while ATC codes are international. This goes beyond the schema and annotations, providing behavioral and data-scope transparency.

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 well-structured and front-loaded with the main purpose. The bullet-point list of use cases is concise and scannable. The final caveat about US-centric data is relevant and non-repetitive, and every sentence earns its place.

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 one-parameter list tool with an output schema and strong annotations, the description covers purpose, use cases, return field nuance, and data scope caveat. It doesn't mention pagination or limiting, but such details are typically not critical for a straightforward listing operation, and the existing schema and annotations fill the gap.

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 provides 100% coverage for atc_code, including a full description of level behavior (levels 1-4 return all members, level 5 returns a single substance). The description reinforces this with an example but doesn't add substantial new information about the parameter itself, so a baseline score of 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 uses a specific verb ('List') and resource ('drugs that belong to an ATC class'), making the tool's purpose immediately clear. It distinguishes from sibling tools like atc_lookup (which likely provides code details) and atc_classify (which assigns ATC classes) by focusing on enumerating class members. A concrete example (A10BA → metformin, phenformin) further anchors the purpose.

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 provides three explicit use cases ('Enumerate all members...', 'Build a list of drugs sharing a pharmacological mechanism', 'Explore an ATC subtree at any level'), which clearly establish when to use the tool. However, it does not explicitly mention alternatives or when not to use it, such as differentiating from atc_lookup for single-code lookups.

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