Skip to main content
Glama
Open Drug Data MCP
by knorby

Get one product record from an open drug data source

drugdata_get_product
Read-onlyIdempotent

Fetch one product record using a source and its own ID from openFDA, DSLD, DailyMed, or INKEEDecoder, returning source details, ingredients, links, and follow-up calls.

Instructions

Use this for an existing source+id, including an entity record or confirmed link; do not repeat a broad search. Fetch only needed records; selectively fetch supplied URLs with host web tools if more page content is needed. Fetch one product record from openFDA, DSLD, DailyMed, or INKEEDecoder. The id is the database's own key: a product NDC (openFDA), a numeric label id (DSLD), an SPL set id (DailyMed), or a product slug/URL (INKEEDecoder). The result carries the unified product ref, source-specific details, ingredient rows (roles, quantities, UNIIs when supplied by the source), links, and suggested follow-up calls. openFDA directory ingredient rows may lack identifiers. For SPL label UNIIs use drugdata_resolve_identifiers with include_label_ingredients: true. include_ingredients is true by default; false also skips DSLD ingredient mapping and enrichment. include_ingredient_enrichment adds DSLD nutrient CAS/group metadata with up to 20 extra serial requests, default false; it has no effect when ingredients are omitted. include_label_sections extracts DailyMed SPL usage sections — these are large and default false. page pages the ingredient and label-section collections one page at a time and re-fetches the record; it never walks pages automatically. A malformed id is an error result naming the search tool that finds a valid one; an upstream miss is an error result, not an empty product.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "source": "<source>",
      "id": "<id>"
    },
    "name": "drugdata_get_product"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe database's own identifier: product NDC (openfda), numeric label id (dsld), SPL set id (dailymed), or slug/URL (inkeedecoder).
pageNoPage number for ingredient and label-section collections, starting at 1. One page per call; the record is re-fetched and the tool never walks pages automatically.
sourceYesUpstream database that owns the record: 'openfda', 'dsld', 'dailymed', or 'inkeedecoder'.
response_formatNoText format: 'markdown' for a readable record, or 'json' for the structured result serialized as JSON.markdown
include_ingredientsNoInclude the product's ingredient rows with roles, quantities, and UNIIs when supplied by the source. openFDA directory rows may lack identifiers; use drugdata_resolve_identifiers with include_label_ingredients: true for SPL label UNIIs. Default true.
include_label_sectionsNoExtract DailyMed SPL usage sections (dosage, directions, patient guidance). Large — default false. Applies to dailymed products; false omits the sections and does not run the section parser.
include_ingredient_enrichmentNoAdd DSLD nutrient CAS/group metadata with up to 20 extra serial requests. Default false. Applies only to dsld when include_ingredients is true; ignored for other sources and when ingredients are omitted.

Output Schema

NameRequiredDescriptionDefault
linksYes
detailsYes
productYes
summaryNoSource-faithful overview assembled from the record.
nextStepsYes
paginationYes
ingredientsNo
labelSectionsNo
labelIngredientsIncludedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds behavior beyond them: malformed ids produce an error naming the tool that finds a valid one, upstream misses are errors rather than empty products, `page` re-fetches the record and never auto-walks, and enrichment can cost up to 20 extra serial requests. It also warns that openFDA directory ingredient rows may lack identifiers and that DSLD mapping is skipped when ingredients are omitted.

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-loaded with routing guidance before the capability statement, and nearly every sentence carries operational weight. It is dense but somewhat meandering, with the purpose statement arriving after the when-to-use sentence and the host-web-tools aside reading awkwardly.

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 7-parameter, multi-source fetch tool with an output schema and rich annotations, the description covers the remaining gaps an agent needs: error semantics for bad ids and upstream misses, pagination limits, and per-flag cost/source applicability. Return contents are summarized at the level needed without duplicating the output schema.

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 schema already carries most parameter meaning; the description still adds interaction semantics not spelled out there, notably that `include_ingredients: false` also skips DSLD ingredient mapping and enrichment and that enrichment has no effect when ingredients are omitted. The id-format mapping across sources largely restates the schema's id description.

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?

States a specific verb and resource: "Fetch one product record from openFDA, DSLD, DailyMed, or INKEEDecoder," and immediately contrasts it with the search path ("do not repeat a broad search"). An agent can distinguish this from drugdata_search_products without opening either schema.

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

Usage Guidelines5/5

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

Gives an explicit precondition ("for an existing source+id, including an entity record or confirmed link"), an explicit exclusion ("do not repeat a broad search"), and routes to a concrete alternative (drugdata_resolve_identifiers with include_label_ingredients: true) for SPL label UNIIs. Cost-based guidance is also given for the enrichment and label-section options.

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