Skip to main content
Glama

search_drug_labels

Read-only

Search openFDA drug labels by brand, generic, or substance name to get matching labels newest first; use returned set IDs to fetch citable passages like boxed warnings and contraindications.

Instructions

Search openFDA drug labels; returns every matching label, newest first. Fetch setid: records for citable passages (boxed_warning, contraindications, ...).

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": {
      "drug": "<drug>"
    },
    "name": "search_drug_labels"
  }
}

Input Schema

NameRequiredDescriptionDefault
drugYesBrand, generic or substance name, e.g. warfarin
limitNo
cursorNo

Output Schema

NameRequiredDescriptionDefault
hitsYes
totalYes
next_cursorNo
source_statusYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description usefully adds that results are complete and ordered newest-first, and it flags the setid: route for citable passages. It does not mention pagination behavior beyond what the cursor param implies, nor any openFDA rate-limit or truncation behavior, which is relevant for an open-world search tool.

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?

Two tight sentences with the core operation front-loaded and the follow-up pointer second. The fragment 'Fetch setid: records for citable passages' is slightly cryptic in its phrasing, but nothing is padded.

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

Completeness3/5

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

An output schema exists, so return-value explanation is not owed. However, for a three-parameter search tool with pagination, the description leaves the limit/cursor mechanics and the actual-vs-every-result framing unaddressed, which an agent needs in order to page correctly.

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

Parameters2/5

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

Schema description coverage is only 33%: only `drug` is documented, while `limit` and `cursor` carry no descriptions and the description does not compensate. Worse, 'returns every matching label' sits awkwardly against a default limit of 10 and a max of 50, and the cursor's role in continuing a result set is never explained.

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 openFDA drug labels') plus the result ordering ('newest first'), which is enough to distinguish a label search from siblings like search_literature or search_trials. The second sentence gestures at a follow-up capability ('Fetch setid: records for citable passages') without naming the sibling tool that performs it, so differentiation is implied rather than explicit.

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?

There is an implicit two-step workflow: search here, then fetch setid: records for citable passages. But no sibling is named and there is no stated when-not-to-use guidance (e.g. searching by setid directly, or preferring fetch_passages when a setid is already known). The guidance is inferable but not actionable on its own.

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