Skip to main content
Glama
google-health-mcp

google-health-mcp

health_get_ecg

Retrieve ECG readings from the watch to check heart rhythm and AFib classifications over a date range, with optional raw waveform samples for trace analysis.

Instructions

Get electrocardiogram (ECG) readings taken on the watch.

Each reading is a single-lead trace the user started by hand, with a rhythm classification - NORMAL_SINUS_RHYTHM, ATRIAL_FIBRILLATION, or one of several inconclusive results (low or high heart rate, poor reading, unclassified). Use it for questions about heart rhythm or AFib checks; for resting rate over time use health_get_heart_rate instead.

Args: start_date: Start date as "YYYY-MM-DD", "YYYY-MM", or "30d". Default: 30 days back from the end date or today, whichever is earlier. end_date: End date as "YYYY-MM-DD", "YYYY-MM" (its last day), or "Nd". Default: today. live: If true, re-fetch this window from the API before reading the cache. include_waveform: If true, include the raw voltage samples. These are thousands of integers per reading - ask for them only to analyse the trace itself. Multiply by scaling_factor for millivolts, and read them at sampling_hz samples per second.

Returns one entry per reading with classification, avg_bpm, duration_sec, sampling_hz, scaling_factor and waveform_samples (null where no trace was stored, or where the stored one cannot be read).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "health_get_ecg"
  }
}

Input Schema

NameRequiredDescriptionDefault
liveNo
end_dateNo
start_dateNo
include_waveformNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.12.0
    • changedOutput schema / (root)
      Previous value: -{
      -  "properties": {
      -    "result": {
      -      "title": "Result",
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "result"
      -  ],
      -  "title": "health_get_ecgOutput",
      -  "type": "object"
      -}New value: +null
  2. First observedv1.0.0

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses data provenance (single-lead traces the user started by hand), cache-vs-API semantics via the live flag, null handling for unreadable/absent waveforms, and the size cost of waveform_samples. It does not cover auth/permission requirements or any latency implication of live re-fetching, which 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?

Purpose and the sibling disambiguation are front-loaded, and each paragraph maps to a distinct need (what it is, args, returns). It is slightly long, but the waveform explanation earns its space because the payload is expensive and needs decoding instructions.

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?

There is no output schema, and the description still specifies the returned fields and their null cases. Combined with full parameter documentation, an alternative-tool pointer, and waveform interpretation guidance, an agent has everything needed to call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate entirely, and it does: every parameter is documented with accepted formats ('YYYY-MM-DD', 'YYYY-MM', '30d', 'Nd'), defaults including the non-obvious earlier-of-two-dates rule, and the meaning of live. It further explains how to interpret waveform output (multiply by scaling_factor for millivolts, read at sampling_hz).

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 first sentence names a specific verb and resource (ECG readings from the watch) and the second sentence enumerates the exact classification values returned, so an agent knows precisely what data this yields. It also explicitly names the sibling health_get_heart_rate and the condition that distinguishes the two.

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 gives a clear when-to-use rule ('questions about heart rhythm or AFib checks') and an explicit alternative for a neighbouring case ('for resting rate over time use health_get_heart_rate instead'). The gap is health_get_irregular_rhythm, an obvious overlapping sibling that is never mentioned or excluded.

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