google-health-mcp

Overview Schema Source Related Servers Discussions Admin

health_get_spo2

Retrieve nightly blood oxygen saturation (SpO2) readings to monitor sleep apnea risk. Run health_sync first to populate the cache.

Instructions

Get nightly SpO2 (blood oxygen saturation) data.

Returns data from the local cache by default. Run health_sync first to populate it.

SpO2 data is sparse: only nights with on-wrist sleep tracking produce readings.

Args: start_date: Start date as "YYYY-MM-DD", "YYYY-MM", or "30d". Default: last 30 days. end_date: End date as "YYYY-MM-DD". Default: today. live: If true, re-fetch this window from the API before reading the cache.

Returns one entry per night: avg SpO2 percentage and up to two pairs of bounds. avg_ci_low/avg_ci_high come from this API, which Google describes as the lower and upper bound of the confidence interval of oxygen saturation samples during sleep. min/max hold whatever an import carried; on the history checked, they matched avg_ci_low/avg_ci_high on every night carrying both. std_dev is Google's standard deviation of the daily SpO2 averages over the past 7-30 days, not of this night's samples, and data_source the device and platform Google says recorded it. Normal range: 95-100%. Below 90% may indicate sleep apnea.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`live`	No
`end_date`	No
`start_date`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Aug 20, 2026

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations provided, the description carries the full behavioral burden and does so well: it discloses the default cached read path, the need to sync first, the sparse nature of SpO2 data, live refetch semantics, return field interpretation, data provenance, and normal/abnormal ranges.

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?

The description is structured with logical sections for usage, args, and returns, and the key cache/live behavior is front-loaded. It is longer than strictly necessary for tool selection because it includes detailed return-field interpretation, but most sentences remain useful.

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 an output schema exists, the description need not explain return structure, but it still provides essential context: cache/live mechanics, sync prerequisite, sparsity caveat, parameter formats, and clinical interpretation. An agent has enough context to call and interpret the tool 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 description coverage is 0%, so the description must compensate. It documents all three parameters: start_date accepted formats and default, end_date format and default, and live behavior. This fully compensates for the schema's lack of parameter descriptions.

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 description states a specific verb and resource: 'Get nightly SpO2 (blood oxygen saturation) data.' It clearly identifies the metric and distinguishes it from sibling health metric tools such as health_get_heart_rate or health_get_sleep.

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 clear prerequisites and cache-vs-live behavior: data comes from the local cache by default, health_sync should run first, and live=true re-fetches from the API. It does not explicitly name alternative tools or when not to use this one, but the metric-specific scope makes that largely unnecessary.

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