Skip to main content
Glama

deviCERTS medical device regulatory data

Get the recalls of a device

get_device_recalls
Read-onlyIdempotent

List the U.S. FDA recalls linked to one device by slug: recall number, FDA recall class (I, II or III), status (ongoing, completed or terminated), start date, reason, and whether the recall names this device or only its shared 510(k) or PMA submission. Optional status filter; newest first, at most 100. Use when the question is about recalls or field safety actions of a known device. Do not use for recalls across devices, by product, firm or date (use search_recalls), for the whole record (use get_device with detail=full) or to find the device (use search_devices). EU devices without an FDA record have no recall data. Read-only, no login. Data: public EUDAMED and U.S. FDA records, synced monthly, EU certificates weekly (dates in get_data_sources). Cached up to 1 hour; limit 300 calls a minute per IP.

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": {
      "slug": "<slug>"
    },
    "name": "get_device_recalls"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugYesDevice slug: the last part of its https://devicerts.com/devices/<slug> URL, as returned by search_devices or find_device_by_identifier. A full page URL or a device:<slug> id is accepted. e.g. heartstart-frx-defibrillator-p180028
statusNoOnly recalls with this FDA status: ongoing, completed or terminated. Default: all.

Output Schema

NameRequiredDescriptionDefault
idYes
noteYes
shownYes
totalYes
deviceYes
formatYes
cite_asYes
recallsYes
retrieved_atYes
status_as_ofYes
canonical_urlYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnly, idempotent, non-destructive), it discloses ordering and truncation ('newest first, at most 100'), caching ('up to 1 hour'), rate limiting ('300 calls a minute per IP'), authentication ('no login'), and data provenance with sync cadence. These are operational traits an agent cannot obtain from the annotations or schema alone.

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?

Purpose, returned fields, usage routing, caveats, and operational limits are laid out in a logical front-loaded order with no filler. Minor waste: the 'EU certificates weekly' sync note is irrelevant to a recall tool and belongs only in get_data_sources, and the field list duplicates what the output schema already provides.

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?

Given an output schema, full schema coverage, and only two parameters, the description covers everything an agent needs: what comes back, ordering, cap size, staleness, rate limits, and which sibling to use instead. Nothing required to call it correctly is missing.

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 slug format examples and a status enum already documented in the schema. The description only reinforces that the slug identifies one device and that status is an optional filter, adding no new syntax or format detail, so the baseline of 3 applies.

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 with explicit scope: 'List the U.S. FDA recalls linked to one device by slug', then enumerates the returned fields (recall number, class, status, date, reason, device-vs-submission linkage). It also names the siblings it is not (search_recalls, get_device, search_devices), so an agent can separate it from them without opening a 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 both when-to-use ('questions about recalls or field safety actions of a known device') and explicit when-not-to-use with the correct alternative for each case (cross-device/product/firm/date recalls → search_recalls; whole record → get_device with detail=full; finding the device → search_devices). It adds a real edge-case caveat: EU devices without an FDA record have no recall data.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.