Skip to main content
Glama

LexGrid EU MDR Medical Devices & Pharma Serialization MCP

EU MDR Annex VIII Medical Device 22 Classification Rules Engine

mdr_device_classification_engine
Read-onlyIdempotent

[EU MDR Annex VIII medical device 22 classification rules engine. Pure statutory logic, read-only, side-effect free]. Determines medical device risk class (Class I, Is, Im, Ir, IIa, IIb, III) under Regulation (EU) 2017/745 Annex VIII based on invasiveness, duration, active functions, and anatomical site, specifying Notified Body conformity assessment routes. Usage: Pass device characteristics and intended purpose to obtain statutory classification, applicable Annexes, and PMS requirements. Returns: JSON object with { deviceName: string, riskClass: string, governingRule: string, notifiedBodyInterventionMandatory: boolean, conformityAssessmentRoutes: array, postMarketSurveillanceRequirement: string, summaryRationale: string }.

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": {
      "deviceName": "<deviceName>",
      "intendedPurpose": "<intendedPurpose>",
      "invasiveness": "<invasiveness>",
      "durationOfUse": "<durationOfUse>",
      "isActiveDevice": "<isActiveDevice>"
    },
    "name": "mdr_device_classification_engine"
  }
}

Input Schema

NameRequiredDescriptionDefault
deviceNameYesCommercial or technical trade name of the medical device
invasivenessYesInvasiveness category ex Annex VIII Section 1
durationOfUseYesDuration of continuous use ex Annex VIII Section 1
isActiveDeviceYesWhether device relies on electrical energy or other power source
intendedPurposeYesClinical intended purpose as stated in instructions for use and labeling
activeDeviceFunctionNoFunctional category for active devices ex Rules 9-12
hasMeasuringFunctionNoWhether device has a statutory measuring function (Class Im)
utilizesNanomaterialsNoRule 19: Whether device consists of or incorporates nanomaterial with exposure potential
absorbedByHumanBodyLocallyNoRule 21: Whether device is composed of substances intended to be absorbed or dispersed
isSterileWhenPlacedOnMarketNoWhether device is delivered sterile (Class Is)
isReusableSurgicalInstrumentNoWhether device is a reusable surgical instrument (Class Ir)
softwareInformsCriticalPatientManagementNoRule 11: Whether software decisions could cause death or irreversible deterioration
incorporatesMedicinalSubstanceAsAncillaryNoRule 14: Whether device incorporates a substance which is a medicinal product if used separately

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, and the bracketed note 'Pure statutory logic, read-only, side-effect free' mostly restates them. What it does add beyond annotations is the determinism/statutory character of the output and the explicit return contract including notifiedBodyInterventionMandatory and postMarketSurveillanceRequirement, but it says nothing about edge cases where multiple rules compete or about determinism guarantees for ambiguous inputs.

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?

Three clearly labeled blocks (scope tag, Usage, Returns) with the purpose stated first and zero filler prose. The Returns enumeration is long but earns its place because no output schema exists. The bracketed tag is mildly redundant with the annotations but does front-load the safety profile.

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

Completeness4/5

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

For a 13-parameter tool with no output schema, the definition supplies both the input intent and a full field list of the JSON response, which is the main gap it needed to close. What remains uncovered is how the many optional boolean flags (isSterileWhenPlacedOnMarket, hasMeasuringFunction, isReusableSurgicalInstrument) interact with the class output, a detail the schema partially handles via inline Rule/Class annotations.

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 rule citations in each parameter description, so the schema already carries the semantic load and the baseline applies. The description's recap of 'invasiveness, duration, active functions, and anatomical site' adds a coarse mental model, though the mention of 'anatomical site' does not map cleanly onto any single parameter. Conditional dependencies (activeDeviceFunction only meaningful when isActiveDevice is true) are not surfaced in the description.

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?

The description names a specific verb and resource: it 'determines medical device risk class (Class I, Is, Im, Ir, IIa, IIb, III) under Regulation (EU) 2017/745 Annex VIII', and enumerates the determining factors (invasiveness, duration, active function). It is unmistakable against generic siblings, but it never names or distinguishes the closest analogue, ai_act_risk_tier_classifier, leaving the agent to infer that this one is MDR-specific rather than AI-Act-specific.

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?

The 'Usage' line tells the agent what inputs to supply and what it will get back, which implies the calling context, but there is no explicit statement of when to use this versus the clinical evaluation screener or the AI Act tier classifier, and no exclusions or preconditions. Guidance is implied rather than stated.

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