Skip to main content
Glama
Open Drug Data MCP
by knorby

Resolve one drug identifier across open data sources

drugdata_resolve_identifiers
Read-onlyIdempotent

Resolve one drug, supplement, or cosmetic identifier across open databases, returning confident cross-source identity links and product ingredient details for unified lookup.

Instructions

Resolve one identifier across openFDA, CosIng, RxNorm, DrugCentral, DailyMed, DSLD, INKEEDecoder, and PubChem. Pass exactly one of unii, ndc, rxcui, cid (PubChem compound id), cas, inci_name, substance_name, spl_setid, or dsld_id. Ingredient identifiers return an identity graph of confident cross-source links with labeled candidate sets for ambiguity; product identifiers (ndc, spl_setid, dsld_id) return the product's cross-source links plus its ingredient rows. include_label_ingredients parses SPL XML for ingredient UNIIs — extra request, default false. resolve_ingredients runs the full resolution per ingredient — many requests on multi-ingredient products, default false — and returns graphs for a prefix of the ingredient rows, capped at 20. max_candidates caps the options per ambiguous source result. Results carry a compact confidence count and suggested follow-up calls. An identifier of the wrong shape is an error result naming the search tool that finds a valid one; zero matches are ordinary and in-band.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "drugdata_resolve_identifiers"
  }
}

Input Schema

NameRequiredDescriptionDefault
casNoCAS Registry Number in dashed form, for example "50-78-2".
cidNoPubChem compound identifier — a positive safe integer, for example "56843331".
ndcNoNational Drug Code — a 10- or 11-digit package NDC or a labeler-product NDC such as "00093-1046".
uniiNoFDA Unique Ingredient Identifier — exactly 10 letters or digits, for example "R16CO5Y76E".
rxcuiNoRxNorm concept identifier — numeric, for example "1191".
dsld_idNoNIH DSLD label id — a positive integer, as a number or digits.
inci_nameNoINCI (cosmetic ingredient) name; a name lookup, not an exact identifier.
spl_setidNoDailyMed Structured Product Label set id — UUID-shaped, for example "a1e07d5c-2056-46f3-8737-f03ed0b4bae8".
max_candidatesNoMaximum candidate options kept per ambiguous source result, 1-10. Default 5.
substance_nameNoSubstance or ingredient name; a fuzzy name lookup when no identifier is known.
response_formatNoText format: 'markdown' for a readable identity report, or 'json' for the structured result serialized as JSON.markdown
resolve_ingredientsNoRuns full resolution per ingredient — many requests on multi-ingredient products, default false.
include_label_ingredientsNoParse SPL XML for ingredient UNIIs — extra request, default false.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the read-only/idempotent annotations by disclosing cost and volume behavior: include_label_ingredients triggers extra requests, resolve_ingredients runs full resolution per ingredient and returns graphs only for a capped prefix of 20 rows. It also distinguishes error semantics (wrong-shaped identifier is an error naming a search tool) from zero matches, which are ordinary and in-band — a meaningful disclosure that prevents an agent from treating an empty result as a failure.

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?

Front-loads scope, then the exactly-one constraint, then return shape, then flag caveats — a logical progression with no filler sentences. It is dense and longish, but nearly every clause carries operational information an agent needs.

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

Completeness5/5

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

For a 13-parameter, multi-source resolution tool this covers the decision-critical facts: which identifier to supply, what each identifier class returns, which flags are expensive, how ambiguity and candidates are bounded, and how failures differ from empty results. Return values are summarized despite an output schema already existing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline would be 3, but the description adds the exclusive-choice constraint the schema cannot express (required is empty, yet exactly one identifier must be passed) and explains the real cost of the two boolean flags plus what max_candidates caps. That is genuine meaning beyond the structured fields.

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

Purpose5/5

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

Opens with a specific verb+resource ("Resolve one identifier") and enumerates the exact data sources covered, then splits behavior by identifier class (ingredient vs product). An agent can distinguish this from the sibling get_/search_ tools from the description alone.

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

Usage Guidelines4/5

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

States the core selection rule ("Pass exactly one of unii, ndc, rxcui, ...") and routes invalid input to the search tool that can find a valid identifier. It also implies when each family applies: ingredient identifiers for identity graphs, product identifiers for product links. No explicit statement of when to prefer drugdata_get_ingredient or the search siblings, so it stops short of full alternative routing.

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