mcp-google-health

list_data_points

Read-only

Retrieve raw Google Health data points by type, newest first, and filter results by time fields using AIP-160 expressions. Use it to inspect steps, sleep, heart rate, and other health records.

Instructions

List raw data points of one data type, newest first. Filter with AIP-160 on the type's time field, for example steps.interval.civil_start_time >= "2026-11-01", weight.sample_time.physical_time >= "2026-11-01T00:00:00Z", daily_resting_heart_rate.date >= "2026-11-01", or sleep.interval.civil_end_time >= "2026-11-01". Use snake case in filters.

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": {
      "dataType": "<dataType>"
    },
    "name": "list_data_points"
  }
}

Input Schema

Name	Required	Description
`filter`	No	AIP-160 filter on the data type's time field.
`dataType`	Yes	Data type in kebab case, such as steps, sleep, or heart-rate. See list_data_types.
`pageSize`	No
`pageToken`	No	nextPageToken from the previous response.
`apiVersion`	No	API version. Defaults to v4, or v4beta for beta-only data types.
`dataSourceFamily`	No	Data sources: all-sources (default), google-wearables (Fitbit and Pixel devices only), google-sources (Google devices, manual logs, Health Connect), or self-sources (data this client wrote).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 10, 2026

TDQS

A3.7/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, covering the safety profile. The description adds real behavioral context beyond them — result ordering ('newest first') and the filter/case conventions — but says nothing about pagination behavior, volume limits, or result shape, which matter for a read tool capped at pageSize 10000.

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 is front-loaded in the first clause, and every subsequent sentence is operational guidance rather than filler. The four filter examples are individually useful but collectively a bit padded — two would establish the pattern — so it is efficient without being maximally tight.

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

Completeness3/5

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

This is a moderately complex, six-parameter read tool with no output schema, so the description bears some burden for describing what comes back. It covers filtering and ordering well but never sketches the shape of a returned data point or notes pagination via nextPageToken, leaving the agent to infer the response by trial.

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

Parameters4/5

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

Schema coverage is 83%, so most parameters are already documented and the baseline is 3. The description still adds meaningful value by explaining that the filter targets each type's specific time field (with per-type field naming examples) and that filter values use snake case while dataType uses kebab case — a distinction the schema alone does not make.

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 opens with a specific verb+resource+scope: 'List raw data points of one data type, newest first.' 'Raw' implicitly contrasts with the roll-up siblings (daily_roll_up_data_points, roll_up_data_points), but it never names an alternative explicitly, so the differentiation is inferential rather than stated.

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 supplies concrete, actionable guidance on how to use the filter parameter, including four worked examples tied to specific data types' time fields and the 'use snake case in filters' rule, which is easy to get wrong. It does not say when to prefer this over roll_up_data_points or get_data_point, so exclusions are absent.

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