Skip to main content
Glama
mymedi-ai-mcp-server

mymedi-ai-mcp-server

by MyMedi-AI

Drug label data with an LLM summary (openFDA)

drug_enrich
Read-only

Look up a drug by brand or generic name in openFDA to retrieve its first matching FDA label, including indications, warnings, dosage, adverse reactions, and interactions, plus a labeled LLM summary.

Instructions

Look up a drug by brand or generic name in openFDA and return its first matching FDA label: brand and generic name, manufacturer, NDCs, route, substance, product type, and the label's indications, warnings, dosage and administration, adverse reactions and drug-interactions sections (null when the label has no such section). Adds an LLM-generated summary, labelled as such: the therapeutic class and the indications the label states. It gives no treatment advice, does not check interactions between drugs, and makes no prior-authorization, coverage or cost determination. A failed call (drug not found, openFDA or the model unavailable) is refunded.

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": {
      "drugName": "<drugName>"
    },
    "name": "drug_enrich"
  }
}

Input Schema

NameRequiredDescriptionDefault
drugNameYesDrug name (brand or generic, min 2 chars)
searchFieldNoMatch the name against the label's brand name or generic name (default: brand_name)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.7.9
    • addedInput schema / properties / drugName / maxLength
      Added value: +500
    • changedInput schema / properties / searchField / description
      Previous value: -"Search by brand or generic name"New value: +"Match the name against the label's brand name or generic name (default: brand_name)"
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations cover the safety profile (readOnly, non-destructive, open-world), and the description adds genuinely non-obvious behavior on top: only the FIRST matching label is returned, missing label sections come back as null rather than erroring, the summary is LLM-generated and labelled as such, and failed calls are refunded. The refund-on-failure and first-match-only semantics are the kind of detail an agent cannot get from any structured field.

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

Conciseness5/5

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

Four sentences, each doing distinct work: what is returned, what the LLM adds, what it refuses to do, and what happens on failure. The returned-field enumeration is dense but front-loaded and necessary given there is no output schema.

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?

With no output schema, the description carries the return-value burden itself and does so thoroughly, including null-section behavior and the LLM summary caveat. Failure modes (drug not found, openFDA or model unavailable) and the refund are also disclosed, leaving no obvious gap for an agent calling this correctly.

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 both parameters are already documented; the description reinforces the brand-vs-generic matching axis that searchField controls. It does not restate the default (brand_name) or the 2-char minimum, but the schema already carries those, so this is a modest addition above 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?

States a specific verb and resource ('look up a drug by brand or generic name in openFDA') and then enumerates exactly what comes back: names, manufacturer, NDCs, route, substance, product type, and specific label sections. The exclusion sentence ('does not check interactions between drugs, makes no prior-authorization, coverage or cost determination') cleanly separates it from drug_interactions, pa_required_check and the reimbursement siblings.

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?

Clearly delimits scope with three negative conditions (no treatment advice, no cross-drug interaction checking, no PA/coverage/cost determinations), which implicitly routes the agent to siblings for those needs. It never names an alternative tool explicitly or states the positive trigger condition (e.g. 'use when you need label text for a specific drug'), so routing is inferential rather than spelled out.

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