Skip to main content
Glama

Dailymed

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Get Drug

get_drug
Read-onlyIdempotent

FULL FDA DRUG LABEL TEXT from the current DailyMed Structured Product Label — indications, dosage and administration, contraindications, warnings and precautions, boxed warning, adverse reactions, and every other labeled section, as readable plain text. Pass a DRUG NAME ("Ozempic", "ibuprofen") and it resolves the label automatically, or a DailyMed set_id. PREFER OVER WEB SEARCH for "what are the warnings for X", "what is X indicated for", "what is the dose of X", "does X have a boxed warning". Returns the label title, labeler, SPL version and publication date alongside the sections.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
set_idNoDailyMed SET ID UUID, when you already have one. Takes precedence over drug_name.
sectionNoOptional case-insensitive substring filter, matched against both the section heading and its LOINC category, e.g. "boxed warning", "warnings", "dosage", "indications". Omit for the whole label.
drug_nameNoDrug brand or generic name (e.g. "Ozempic", "ibuprofen"). Resolved to the primary manufacturer's label. Use this OR set_id.
max_section_charsNoTruncate each section body to this many characters (default 4000, max 40000).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
ndcNoNDC codes
nameNoDrug name
rxcuiNoRxNorm RxCUI codes
setIdNoDailyMed unique identifier
sectionsNoSPL sections (dosage, warnings, adverse reactions, etc.)
lastUpdateNoISO date of last update
manufacturerNoManufacturer name
applicationNumberNoNDA/ANDA number

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "set_id": "fdbfe194-b845-42c5-bb87-a48118bc72e7"
-  }
-]New value: +[
+  {
+    "drug_name": "ibuprofen"
+  },
+  {
+    "drug_name": "Ozempic",
+    "section": "boxed warning"
+  }
+]
    • addedInput schema / properties / drug_name
      Added value: +{
+  "description": "Drug brand or generic name (e.g. \"Ozempic\", \"ibuprofen\"). Resolved to the primary manufacturer's label. Use this OR set_id.",
+  "type": "string"
+}
    • addedInput schema / properties / max_section_chars
      Added value: +{
+  "description": "Truncate each section body to this many characters (default 4000, max 40000).",
+  "type": "number"
+}
    • addedInput schema / properties / section
      Added value: +{
+  "description": "Optional case-insensitive substring filter, matched against both the section heading and its LOINC category, e.g. \"boxed warning\", \"warnings\", \"dosage\", \"indications\". Omit for the whole label.",
+  "type": "string"
+}
    • changedInput schema / properties / set_id / description
      Previous value: -"DailyMed setId UUID"New value: +"DailyMed SET ID UUID, when you already have one. Takes precedence over drug_name."
    • removedInput schema / required
      Removed value: -[
-  "set_id"
-]
  2. Changed1 schema field changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "set_id": "3d50d4d9-3f05-4cd8-baaa-5e6a9eef0d2f"
-  }
-]New value: +[
+  {
+    "set_id": "fdbfe194-b845-42c5-bb87-a48118bc72e7"
+  }
+]
  3. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "set_id": "3d50d4d9-3f05-4cd8-baaa-5e6a9eef0d2f"
+  }
+]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "description": "Full Structured Product Label with metadata and sections",
+  "properties": {
+    "applicationNumber": {
+      "description": "NDA/ANDA number",
+      "type": "string"
+    },
+    "lastUpdate": {
+      "description": "ISO date of last update",
+      "type": "string"
+    },
+    "manufacturer": {
+      "description": "Manufacturer name",
+      "type": "string"
+    },
+    "name": {
+      "description": "Drug name",
+      "type": "string"
+    },
+    "ndc": {
+      "description": "NDC codes",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "rxcui": {
+      "description": "RxNorm RxCUI codes",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "sections": {
+      "description": "SPL sections (dosage, warnings, adverse reactions, etc.)",
+      "items": {
+        "properties": {
+          "content": {
+            "description": "Section content HTML or plain text",
+            "type": "string"
+          },
+          "sectionName": {
+            "description": "Section title (e.g. DOSAGE, WARNINGS)",
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "setId": {
+      "description": "DailyMed unique identifier",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
  4. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false. The description adds useful behavioral context beyond those: it returns the current label as plain text, resolves a drug name to the primary manufacturer's label, includes SPL version and publication date, and supports a section filter. There is no contradiction with the annotations.

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 description is three dense, purposeful sentences with the most important content front-loaded ('FULL FDA DRUG LABEL TEXT' and 'PREFER OVER WEB SEARCH'). The repeated query examples and metadata list earn their place, though the all-caps emphasis and example redundancy add slight noise.

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?

Given the annotations, output schema, and sibling tool list, the description covers the source, resolution behavior, return metadata, and preferred usage scenarios. It is complete enough for an agent to select and call the tool correctly, though it does not explicitly distinguish this from the related label tools (label_diff, label_history, list_labels_for_drug_name).

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%, with all four parameters already documented and an example for each usage mode. The description reinforces the drug_name vs set_id distinction but does not meaningfully explain max_section_chars or the section-substring behavior beyond what the schema already provides, so it stays at the baseline.

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?

The description opens with 'FULL FDA DRUG LABEL TEXT' and names the exact resource (current DailyMed Structured Product Label) and scope ('indications... every other labeled section'), so the verb+resource is specific. It also differentiates itself by positioning the tool as the full-label source and by naming the returned metadata (label title, labeler, SPL version, publication date).

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?

The description gives explicit usage context: when to prefer this over web search, with example queries like 'what are the warnings for X' and 'what is the dose of X'. It also explains the two input routes (drug name or set_id). It stops short of naming sibling alternatives such as label_diff or label_history or stating when not to use the tool, so it is clear but not fully exhaustive.

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

All Dailymed toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources