Skip to main content
Glama

Umls Search

umls_search
Read-onlyIdempotent

Search clinical terms/codes -> UMLS concepts (CUIs). Maps free text or a source code to UMLS concept unique identifiers spanning SNOMED CT, ICD-10, RxNorm, LOINC, MeSH, etc. Example: umls_search({ query: "myocardial infarction", _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": {
      "query": "myocardial infarction",
      "_apiKey": "your-umls-api-key"
    },
    "name": "umls_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesA clinical term, phrase, or source code to search, e.g. "heart attack" or "410.0"
sourceNoOptional source vocabulary abbreviation (SAB) to restrict results, e.g. "SNOMEDCT_US", "ICD10CM", "RXNORM", "LNC", "MSH". Comma-separate for multiple.
_apiKeyYesFree UMLS UTS API key (from your UTS profile at uts.nlm.nih.gov)
return_typeNoOptional identifier type to return: "concept" (default, CUIs), "code" (source codes), or "sourceConcept".

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 readOnly, idempotent, non-destructive and open-world behavior, so the bar is lower. The description adds genuine context by naming the vocabularies that can be mapped and the CUI output form, but says nothing about result cardinality, ranking, ambiguity handling, or UTS API-key rate limits.

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?

The mapping is front-loaded in one clause and the example is compact. Minor redundancy: the inline example largely duplicates the schema's examples array and the _apiKey placeholder.

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 read-only, four-parameter search with no output schema and full schema coverage, the definition supplies enough to call it correctly. Remaining gaps are response shape and any API key constraints or rate limits, which are secondary.

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%, so all four parameters (including return_type's concept/code/sourceConcept values and the SAB format) are already documented in the schema. The description's example adds a little operational context but no semantics beyond what the schema provides.

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?

States a specific verb and resource ('Search clinical terms/codes -> UMLS concepts (CUIs)') and names the vocabulary families spanned (SNOMED CT, ICD-10, RxNorm, LOINC, MeSH). It does not distinguish itself from close siblings like umls_concept or umls_crosswalk, so it falls short of a 5.

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 implied by the examples (free text like "myocardial infarction" or a source code like "410.0"), but there is no explicit when-to-use/when-not guidance and no pointer to alternatives such as umls_concept for CUI detail or umls_crosswalk for vocabulary translation.

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.