mcp-google-health

roll_up_data_points

Read-only

Aggregates Google Health data points into fixed physical-time windows, such as hourly steps or 5-minute heart rate, for trend analysis over a date range.

Instructions

Aggregate a data type into fixed physical-time windows, such as hourly steps or 5-minute heart rate. Range is closed-open; at most 14 days for heart-rate, active-minutes, total-calories, and calories-in-heart-rate-zone, 90 days otherwise.

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>",
      "startTime": "<startTime>",
      "endTime": "<endTime>",
      "windowSize": "<windowSize>"
    },
    "name": "roll_up_data_points"
  }
}

Input Schema

Name	Required	Description
`endTime`	Yes	RFC 3339 timestamp.
`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.
`startTime`	Yes	RFC 3339 timestamp.
`apiVersion`	No	API version. Defaults to v4, or v4beta for beta-only data types.
`windowSize`	Yes	Window length in seconds with an s suffix, such as 3600s.
`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

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds genuine behavioral context with the closed-open interval convention and per-data-type range caps. It omits what error or truncation occurs when a range exceeds the limit, and says nothing about how paginated results are returned despite pageSize/pageToken being present.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tightly packed sentences with zero filler: the aggregation semantics and window examples come first, followed by the range semantics and limits. Every clause carries actionable information.

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 an 8-parameter, no-output-schema read tool, the description covers the essential semantics (window definition, range convention, per-type limits). The remaining gap is pagination expectations for large results and failure behavior at the range boundary, which the schema alone does not resolve.

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 description coverage is 88%, so the baseline is 3, and the description earns an upgrade by clarifying two schema-ambiguous points: that startTime/endTime form a closed-open range, and that windowSize is a fixed physical duration (with '3600s'-style examples). The 14/90-day limits also give the agent an implicit rule linking dataType choice to usable time spans.

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?

States a specific verb (aggregate) and resource (a data type) plus the key differentiator: fixed physical-time windows, illustrated with 'hourly steps or 5-minute heart rate'. An agent can distinguish it from calendar-day aggregation siblings, though the description never names daily_roll_up_data_points explicitly.

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?

Gives usage-relevant constraints (closed-open range, 14-day cap for heart-rate/active-minutes/total-calories/calories-in-heart-rate-zone, 90 days otherwise) and concrete window examples. However, it does not say when to prefer this over daily_roll_up_data_points or list_data_points, nor what happens if the range limit is exceeded.

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