Skip to main content
Glama

Meridian Trace — Medical Device Registrations

Classify a device type

classify_device
Read-onlyIdempotent

RUNS WITHOUT AN API KEY (anonymous callers see the top 3 FDA product codes and the full per-market risk table — a free key unlocks the rest). Classification view of a device type: the GMDN hierarchy it sits in, the FDA product codes it maps to with how many devices carry each, and — the part not published anywhere — how the SAME device type is actually risk-classed market by market, with the sample size behind each. Risk class is not portable: a device type can be modal High in Canada and modal Medium in the EU and Singapore, which changes submission route, evidence burden and timeline. Observed practice, not a regulatory determination. Takes a plain device name ("bone screw", "hip implant"), a GMDN code, or an FDA product code. A name is resolved by how many real devices carry each GMDN term rather than by string matching, and resolution reports which term was chosen, how many others matched and what they were — call again with gmdn_code to classify one of those instead.

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": {
      "reason": "<reason>",
      "user_intent": "<user_intent>"
    },
    "name": "classify_device"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasonYesA short phrase saying why you are calling this tool, for example: find unpaid invoices.
gmdn_codeNoGMDN code, e.g. "44727"
device_typeNoA device name in plain words ("insulin pump", "orthopaedic plate") or a GMDN term. US and British spellings both resolve. Name the device, not the brand or the use — "infusion pump", not "PumpMaster 3000" or "for giving fluids". Where the name fits several device types, the reply says so in `resolution`.
user_intentYesOne sentence describing what the user is trying to accomplish. Keep it the same across calls until the user's goal changes.
fda_product_codeNoFDA product code, e.g. "DZE"

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / reason
      Added value: +{
      +  "description": "A short phrase saying why you are calling this tool, for example: find unpaid invoices.",
      +  "maxLength": 128,
      +  "minLength": 1,
      +  "type": "string"
      +}
    • addedInput schema / properties / user_intent
      Added value: +{
      +  "description": "One sentence describing what the user is trying to accomplish. Keep it the same across calls until the user's goal changes.",
      +  "maxLength": 256,
      +  "minLength": 1,
      +  "type": "string"
      +}
    • addedInput schema / required
      Added value: +[
      +  "reason",
      +  "user_intent"
      +]
  2. Changed1 schema field changed
    • changedInput schema / properties / device_type / description
      Previous value: -"GMDN term or partial term, e.g. \"Dermatome\""New value: +"A device name in plain words (\"insulin pump\", \"orthopaedic plate\") or a GMDN term. US and British spellings both resolve. Name the device, not the brand or the use — \"infusion pump\", not \"PumpMaster 3000\" or \"for giving fluids\". Where the name fits several device types, the reply says so in `resolution`."
  3. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description adds real behavior beyond them: anonymous callers get only the top 3 FDA product codes, a free key unlocks the rest, name resolution is frequency-based rather than string matching, and results are observed practice rather than a regulatory determination. The absence of pagination/rate-limit detail keeps it short of a 5.

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 content is dense and each sentence carries information, but the opening API-key notice precedes the statement of what the tool does, and the em-dash-heavy sentences are long. Front-loading the classification purpose would improve scanability, though nothing is genuinely wasted.

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 still enumerates the return shape (GMDN hierarchy, FDA codes with counts, per-market risk classes with sample sizes, and a `resolution` object), plus the marketplace consequence of divergent risk classes. An agent has everything needed to call it and interpret the reply.

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 coverage is 100%, so the baseline is 3; the description does add meaning by explaining that `device_type` should be a generic device name not a brand and that `gmdn_code` is the disambiguation path. It says nothing about `reason` or `user_intent`, though the schema already documents those in full.

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 states a specific verb and resource — classification of a device type into its GMDN hierarchy, mapped FDA product codes with device counts, and a per-market risk-class table with sample sizes. That is a distinct payload no sibling (find_similar_devices, get_registration, search_manufacturer) would return, so an agent can differentiate without opening another schema.

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?

It specifies the accepted identifier forms (plain device name, GMDN code, FDA product code) and gives an explicit follow-up protocol: if `resolution` reports multiple matches, call again with `gmdn_code`. It also warns to name the device rather than a brand. What it lacks is any explicit routing against sibling tools for related questions.

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.

Resources