Skip to main content
Glama

Umls Atoms

umls_atoms
Read-onlyIdempotent

Source codes (ICD/SNOMED/RxNorm/LOINC) for a concept. Lists the source-asserted atoms of a CUI, the actual codes and names each vocabulary uses for that concept (the crosswalk table). Example: umls_atoms({ cui: "C0027051", _apiKey: "your-key" })

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "cui": "C0027051",
      "_apiKey": "your-umls-api-key"
    },
    "name": "umls_atoms"
  }
}

Input Schema

NameRequiredDescriptionDefault
cuiYesUMLS Concept Unique Identifier, e.g. "C0027051"
_apiKeyYesFree UMLS UTS API key

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is fully covered. The description adds conceptual context about what an 'atom' is (source-asserted codes and names per vocabulary) but says nothing about result size, pagination, or typical fan-out for popular concepts. Useful content framing, no added behavioral traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short, front-loaded sentences: purpose, then definition of 'atoms', then example. Nothing is padded, though the worked example largely repeats the schema's own example and could be dropped without loss.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter read tool with full schema description coverage and complete annotations, the definition is essentially sufficient — it explains what the returned atoms represent. The remaining shortfall is the unresolved overlap with the umls_crosswalk and umls_concept siblings, plus no hint about result volume.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and both parameters (cui, _apiKey) are documented in the schema, so the baseline of 3 applies. The inline example duplicates the schema example's CUI (C0027051) without adding format, validation, or edge-case meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb plus resource: it 'lists the source-asserted atoms of a CUI' and names the concrete vocabularies involved (ICD/SNOMED/RxNorm/LOINC). It is clear what you get back, but it does not distinguish itself from the sibling tools umls_crosswalk and umls_concept — in fact it calls itself 'the crosswalk table,' which blurs the boundary with umls_crosswalk.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Use is only implied: an agent can infer you call this when you have a CUI and need per-vocabulary codes. There is no explicit when-to-use versus umls_crosswalk, umls_concept, or umls_search, and no note on prerequisites beyond the API key in the schema. Given a near-namesake sibling, this is a meaningful gap.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.