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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered structurally. The description adds that output is source-asserted codes/names across vocabularies and shows an example invocation including the _apiKey requirement, but says nothing about result size, pagination, or latency for a concept that may map to many atoms. Modest value beyond annotations.

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?

Two compact sentences with the return content front-loaded, followed by an example. Efficient and readable. The inline example largely duplicates the schema's examples array, a minor redundancy that keeps it from a 5.

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?

No output schema exists, and the description compensates by explaining what the atoms are (codes and names each vocabulary assigns to the CUI). With annotations covering safety, params fully documented in the schema, and return content described, an agent has what it needs to call correctly.

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 100% — both cui and _apiKey are described in the schema, including CUI format and that the key is a free UMLS UTS key. The description only repeats the example CUI value and does not add format, constraint, or edge-case semantics (e.g., what happens with an invalid or non-existent CUI). Baseline 3 applies.

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?

States a specific verb ('lists') and resource ('source-asserted atoms of a CUI'), plus concrete vocabularies (ICD/SNOMED/RxNorm/LOINC), so the agent knows exactly what comes back. It does not, however, differentiate itself from siblings like umls_crosswalk or umls_concept — calling itself 'the crosswalk table' arguably blurs the line with umls_crosswalk rather than sharpening it.

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?

Usage is implied by the content description (use it to get per-vocabulary codes for a CUI), but there is no explicit when-to-use, when-not, or pointer to umls_crosswalk/umls_concept/umls_search. The agent must infer the selection rule from the return-content description alone.

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