google-health-mcp

Overview Schema Source Related Servers Discussions Admin

health_trends

Compute averages and totals over time from cached Google Health data, auto-syncing when stale. Compare periods across activity, sleep, heart rate, and more.

Instructions

Analyse trends in cached health data.

Computes averages and totals over time from the local cache, auto-syncing if stale.

Args: data_type: What to analyse. Options: "heart_rate", "activity", "exercises", "sleep", "weight", "spo2", "hrv", "azm", "breathing_rate", "skin_temperature", "core_temperature", "cardio_fitness", "food_log". Default: "activity". period: Aggregation period. Options: "weekly", "monthly", "quarterly". Default: "monthly". start_date: Start date as "YYYY-MM-DD" or "365d". Default: last 12 months. end_date: End date as "YYYY-MM-DD". Default: today. compare: Compare two periods. Format: "last_30d vs previous_30d", "2026-03 vs 2026-02", "2026-Q1 vs 2025-Q4". When set, period/start_date/end_date are ignored.

Returns aggregated averages per period. For activity: steps, distance, active minutes. For exercises: sessions, duration, calories. For sleep: duration, efficiency, stage breakdown. For heart_rate: resting HR min/avg/max. For weight: weight, fat%, BMI. For hrv: daily and deep RMSSD.

For cardio_fitness, avg_vo2_max_low/high average a reported band while avg_vo2_max averages a single value: two definitions, each with the count of readings behind it, never one series.

For spo2, min_spo2/max_spo2 are the lowest and highest bound among imported nights (counted by nights_observed_extremes), and avg_nightly_ci_low/avg_nightly_ci_high the mean of the nightly bounds this API reports (counted by nights_confidence_interval).

These fields and their counts appear in the period form only. compare= reports spo2 as avg_spo2 alone, and carries both cardio_fitness definitions.

For core_temperature, a reading whose value was changed in the app is counted as well as its earlier value, in both forms: check a high max_temp_celsius or readings_ge_38c with health_get_core_temperature.

Not for raw data - use health_get_* tools instead.

Input Schema

TableJSON Schema

Name	Required	Default
`period`	No	monthly
`compare`	No
`end_date`	No
`data_type`	No	activity
`start_date`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv1.7.0Sep 30, 2026

addedInput schema / properties / data_type / enum

Added value: +[
+  "heart_rate",
+  "activity",
+  "exercises",
+  "sleep",
+  "weight",
+  "spo2",
+  "hrv",
+  "azm",
+  "breathing_rate",
+  "skin_temperature",
+  "core_temperature",
+  "cardio_fitness",
+  "food_log"
+]

addedInput schema / properties / period / enum

Added value: +[
+  "weekly",
+  "monthly",
+  "quarterly"
+]

First observedv1.0.0Aug 20, 2026

TDQS

A4.4/5.0

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 delivers: it discloses cache-backed reads, auto-sync-if-stale behavior, the compare-mode override semantics, spo2/cardio_fitness dual-definition quirks, and that edited core_temperature readings are double-counted. It does not state read-only/destructive posture explicitly, but 'analyse' strongly implies a read.

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

Conciseness3/5

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

The Args block is well front-loaded and cleanly organized, but roughly half the text explains return-field semantics for spo2, cardio_fitness, and core_temperature even though an output schema exists, which is verbose for a description.

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?

Given 5 undocumented params, no annotations, and the analytical complexity, the description covers inputs, caching/sync behavior, comparison mode, per-datatype return semantics, and edge cases, leaving nothing an agent needs to call it correctly unaddressed.

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 and does so fully: it enumerates each param, lists the allowed enum values for data_type and period, gives defaults, date formats ('YYYY-MM-DD' or '365d'), and worked compare examples with the override rule.

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 ('Analyse trends in cached health data', computing averages/totals over time) and explicitly distinguishes itself from the health_get_* raw-data siblings. An agent can identify the tool's scope without opening the 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?

Explicitly routes raw-data needs to health_get_* tools and explains that compare overrides period/start_date/end_date. It gives clear usage context but does not name a specific alternative sibling (e.g. health_get_lifetime_stats) for cases where trends is wrong.

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