Skip to main content
Glama

Meridian Trace — Medical Device Registrations

List registrations

get_registrations
Read-onlyIdempotent

Every individual registration held by a manufacturer — product name, registration number, status, dates, risk class and source registry — filterable by market and status. Each row also carries an enrichment block Meridian derived: device class as a RANK on that market's own scale ("3 of 4") rather than a label that means different things in different markets, the resolved device type, the clinical area with the number of signals that agreed on it, the FDA product code, country of origin, brand and intended use. Each row carries a provenance block naming any field Meridian derived (inferred, classified, translated) with a confidence band where one applies; every field NOT listed there is the registry's own value, unmodified. Use that to lean on verbatim fields and hedge on derived ones. Use get_market_coverage instead when the question is which markets a company is in.

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": {
      "manufacturer_id": "<manufacturer_id>",
      "reason": "<reason>",
      "user_intent": "<user_intent>"
    },
    "name": "get_registrations"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage number (default 1)
limitNoResults per page (default 50, max 200)
marketNoFilter to a single market — ISO2 code (e.g. "SG") or full name (e.g. "Singapore")
reasonYesA short phrase saying why you are calling this tool, for example: find unpaid invoices.
statusNoFilter by lifecycle state: "active", "expired", "cancelled" or "pending". These are applied as RULES, not string matching — a market that publishes no status (Israel, Mexico, China) is resolved from its expiry date, and registry wording ("Cleared", "Approved", "Registered") is normalised. Any other value falls back to a literal match on the registry's own status string.
user_intentYesOne sentence describing what the user is trying to accomplish. Keep it the same across calls until the user's goal changes.
manufacturer_idYes

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"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "manufacturer_id"
      -]New value: +[
      +  "manufacturer_id",
      +  "reason",
      +  "user_intent"
      +]
  2. Changed1 schema field changed
    • changedInput schema / properties / status / description
      Previous value: -"Filter by registration status string (registry-specific, e.g. \"ACTIVE\", \"Registered\")"New value: +"Filter by lifecycle state: \"active\", \"expired\", \"cancelled\" or \"pending\". These are applied as RULES, not string matching — a market that publishes no status (Israel, Mexico, China) is resolved from its expiry date, and registry wording (\"Cleared\", \"Approved\", \"Registered\") is normalised. Any other value falls back to a literal match on the registry's own status string."
  3. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world, so the safety bar is low; the description nonetheless adds substantial behavioral context beyond them. It explains that derived fields live in an `enrichment` block, that device class is expressed as a rank on each market's own scale precisely because labels are not cross-market comparable, and that `provenance` names every inferred/classified/translated field with a confidence band. That is actionable epistemic guidance an agent cannot get from annotations.

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?

Front-loaded: the resource and its filters come first, then enrichment, then provenance, then the sibling pointer — a sensible order. The sentences are long and dense, and there is minor overlap between 'risk class' in the field list and 'device class as a RANK' in the enrichment block that could read as the same thing, but no sentence is filler.

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?

For a 7-parameter read tool with no output schema, the description carries the full burden of describing the response shape and does so: row fields, the enrichment sub-fields, and the provenance sub-block. Combined with 86% schema coverage on inputs, an agent has everything needed to call it and interpret results 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 86%, so the schema already documents page, limit, market, status, reason and user_intent in detail — including the rule-based status resolution. The description only notes that results are 'filterable by market and status' without adding format or edge-case meaning beyond the schema. Baseline 3 is appropriate; the description neither adds nor omits param meaning.

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 (list registrations held by a manufacturer) and immediately enumerates the returned fields — product name, number, status, dates, risk class, source registry — plus the enrichment and provenance blocks. It also names the sibling it is not (get_market_coverage) and the condition that selects it, so the agent can discriminate 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit routing guidance is given for the closest alternative: use get_market_coverage when the question is which markets a company is in. It also gives interpretive guidance on how to act on results ('lean on verbatim fields and hedge on derived ones'). It stops short of contrasting with get_recent_registrations or get_registration, so it is clear but not exhaustive.

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