Skip to main content
Glama

Openfda

by io.github.pipeworx-io

Fda Warning Letters

fda_warning_letters
Read-onlyIdempotent

Search FDA WARNING LETTERS — official enforcement letters FDA sends firms for violations (CGMP, adulterated/misbranded products, unapproved claims). Answers "has received an FDA warning letter", "recent FDA warning letters about supplements/devices". By default search matches the RECIPIENT company the letter was issued to, so the answer is about that firm's own enforcement history; set match:"fulltext" to search the whole letter record instead, which also finds letters that merely mention a firm. Every row reports matched_field so a caller can tell "issued to" from "mentions". Covers ~3,660 letters. Returns recipient company, posted/issued dates, issuing FDA office, subject, and a link to the full letter text. Keyless, live from fda.gov.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax letters to return, 1–50 (default 10). Newest first.
matchNoHow `search` is applied. "recipient" (default) keeps only letters whose addressed company matches. "fulltext" returns every record matching anywhere in its indexed text, including letters that only mention the term.
searchNoCompany the letter was issued to (e.g. "Elanco", "Merck Sharp & Dohme") under the default match mode. Under match:"fulltext" this is a free-text query over the whole record — a product ("supplement") or violation topic ("CGMP"). Omit for the most recent letters.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed3 schema fields changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "search": "Blooming"
-  },
-  {
-    "limit": 20,
-    "search": "supplement"
-  }
-]New value: +[
+  {
+    "search": "Elanco"
+  },
+  {
+    "limit": 20,
+    "match": "fulltext",
+    "search": "supplement"
+  }
+]
    • addedInput schema / properties / match
      Added value: +{
+  "description": "How `search` is applied. \"recipient\" (default) keeps only letters whose addressed company matches. \"fulltext\" returns every record matching anywhere in its indexed text, including letters that only mention the term.",
+  "enum": [
+    "recipient",
+    "fulltext"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / search / description
      Previous value: -"Full-text search — a company name (e.g. \"Blooming\"), product (\"supplement\"), or violation topic (\"CGMP\"). Omit for the most recent letters."New value: +"Company the letter was issued to (e.g. \"Elanco\", \"Merck Sharp & Dohme\") under the default match mode. Under match:\"fulltext\" this is a free-text query over the whole record — a product (\"supplement\") or violation topic (\"CGMP\"). Omit for the most recent letters."
  2. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "search": "Blooming"
+  },
+  {
+    "limit": 20,
+    "search": "supplement"
+  }
+]
  3. Added

TDQS

A4.5/5.0
Behavior5/5

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

Even with readOnlyHint/idempotentHint annotations already covering the safety profile, the description adds substantial behavioral detail: default recipient matching, fulltext mode semantics, the matched_field output disambiguation, coverage of ~3,660 letters, and the return fields. It also notes the data is keyless and live from fda.gov, which is useful context beyond 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.

Conciseness5/5

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

The description is dense but well-organized: purpose and example questions come first, then matching behavior, then scope, return contents, and data source. Every sentence adds information, and there is no filler or repetition of schema content beyond what is useful for orientation.

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 compensates by listing return fields: recipient company, dates, issuing office, subject, link, and matched_field. It also specifies search semantics, default behavior, coverage size, freshness, and authentication requirement (none), making it sufficiently complete for an agent to call this tool correctly.

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%, and the input schema already thoroughly explains 'search', 'match', and 'limit', including defaults, enums, and the recipient-vs-fulltext distinction. The description mostly reinforces these semantics rather than adding meaningfully new parameter-level detail, so the baseline score of 3 is appropriate.

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 'Search FDA WARNING LETTERS — official enforcement letters FDA sends firms for violations', naming a specific verb, resource, and defining scope. It gives concrete example questions ('has <company> received an FDA warning letter') and distinguishes the tool from siblings like approvals and recalls by focusing on warning letters and recipient enforcement history.

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 provides clear usage context through example queries and explicitly explains when to use the default 'recipient' match versus 'fulltext' search, including that fulltext finds letters that merely mention a firm. It does not name alternatives among sibling tools or state when not to use this tool, so it falls just short of a 5.

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

All Openfda toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation4/5

Most tools have distinct names and purposes, but the large number of meta-tools (e.g., ask_pipeworx variants, deep_research) and overlapping research/scanning tools (entity_profile, compare_entities, recent_changes) could cause confusion. An agent may need to carefully read descriptions to choose correctly.

Naming Consistency3/5

Snake_case is prevalent but not universal. FDA tools are consistently named with 'fda_' prefix, but there are single-word verbs (remember, recall), camelCase is absent, and some tool names are long and descriptive (scan_competitor_ai_presence). The mix of patterns is readable but not highly consistent.

Tool Count3/5

43 tools is high and includes both dedicated tools and meta-tools that can access thousands more. There is redundancy (e.g., FDA data can be retrieved via fda_drug_approvals or ask_pipeworx). The scope is broad, but many tools could be consolidated. Count feels borderline excessive for the apparent purpose.

Completeness4/5

FDA coverage is excellent with tools for approvals, labels, events, recalls, shortages, warning letters, etc. Other domains (financial, betting, npm) are covered by meta-tools, providing breadth. However, dedicated non-FDA tools are sparse, and the server relies heavily on the universal query tools for completeness.

Resources