Garmin MCP

garmin_stats

Performs statistical analysis on numeric health data. Supports operations like describe, percentiles, correlation, trend, compare, moving averages, and outlier detection.

Instructions

Perform a statistical analysis operation on numeric data.

operation: one of "describe", "percentiles", "correlation", "trend", "compare", "moving_average", "outliers".

Common params: values: primary list of numeric values (required for all operations). y: second list of values (for "correlation" and "compare"). labels: parallel date/label list (for "trend" and "moving_average").

Operation-specific params: describe: (no extra params needed) percentiles: percentiles (list of ranks 0-100, default [5,10,25,50,75,90,95]) correlation: y (required), method ("pearson" or "spearman") trend: labels (optional date labels) compare: y (required sample B), a_label, b_label moving_average: window (default 7), labels outliers: method ("iqr" or "zscore"), threshold (default 1.5)

Examples: Descriptive stats: operation="describe", values=[65,62,68,70,64] Trend analysis: operation="trend", values=[rhr_vals...], labels=[dates...] Correlation: operation="correlation", values=[steps...], y=[sleep_scores...], method="pearson" Compare weeks: operation="compare", values=[this_week...], y=[last_week...], a_label="this_week", b_label="last_week"

Input Schema

TableJSON Schema

Name	Required	Default
`y`	No
`labels`	No
`method`	No	pearson
`values`	Yes
`window`	No
`a_label`	No	sample_a
`b_label`	No	sample_b
`operation`	Yes
`threshold`	No
`percentiles`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 6, 2026

TDQS

A3.9/5.0

Behavior3/5

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

With no annotations, the description carries the full burden of behavioral disclosure. It explains the kinds of operations and their parameter requirements, but it does not explicitly state whether the tool is read-only, what it returns, or how it handles null or misaligned inputs. The presence of an output schema reduces the return-format gap, but side-effect behavior is still implicit.

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?

The description is well organized with general parameters, operation-specific parameters, and examples. It is longer than average, but every section earns its place given the tool's 10 parameters and 6 operation modes, with no redundant filler.

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 a tool with this many operations and parameters, the description is nearly complete: it covers all parameters, per-operation requirements, defaults, and realistic examples. It could additionally clarify null-value handling and the relationship between labels and values, but the output schema covers return expectations.

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, and it does thoroughly. Every parameter in the schema is explained with operation-specific meaning, required status, defaults, and valid choices. The examples further clarify how to combine parameters for different analyses.

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 clearly states that the tool performs statistical analysis on numeric data and enumerates the six supported operations. It is easy to understand what the tool does, but it does not explicitly distinguish itself from overlapping siblings such as garmin_metric, garmin_data, or garmin_viz.

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?

The description gives useful operation-specific usage guidance, including required parameters and defaults, plus examples. However, it never states when to prefer this tool over alternatives or when not to use it, leaving sibling differentiation to inference.

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

Deploy Server