Skip to main content
Glama
Sign In
garmin-mcp

garmin-mcp

by Sinfjell
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

get_performance_metrics

Retrieve a current running fitness snapshot—lactate threshold, VO2 max, fitness age, and race predictions—to see where your training stands today.

Instructions

Get current running fitness/threshold snapshot: lactate threshold, VO2 max, race predictions.

Answers "where is my fitness right now?" in one call. date is optional ("YYYY-MM-DD", defaults to today) and only affects which day's VO2 max is read; lactate threshold and race predictions always return Garmin's latest available values. Returns a JSON object with three independent sections:

  • "lactate_threshold": threshold heart rate (LTHR, bpm) and threshold pace ("M:SS/km" plus decimal min/km and raw m/s) — the numbers used to set training zones. (Garmin's "heart rate threshold" and "lactate threshold" are the same value.)

  • "vo2max": VO2 max (decimal precise value + rounded) and fitness age.

  • "race_predictions": predicted 5k / 10k / half-marathon / marathon finish times as clock strings.

Each section is fetched independently: if one Garmin endpoint is unavailable it becomes {"error": ...} while the others still return. Every section carries its own "measured_date" so stale values are visible.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_performance_metrics"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so: it discloses that each section is fetched independently, that a failing endpoint yields an {"error": ...} for that section only, that each section carries measured_date so stale values are visible, and that threshold/race predictions ignore the date parameter. That is exactly the kind of runtime behavior an agent cannot infer from the schema.

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?

Front-loaded with purpose and the 'in one call' framing, then a bulleted breakdown of the three return sections that is skimmable and earns its space. Some unit-level detail (decimal min/km and raw m/s) is more granular than an agent needs for tool selection, but nothing is padded or circular.

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?

Complete for a one-parameter aggregation tool: purpose, partial-failure semantics, date scoping, and per-section staleness handling are all covered. Since an output schema exists, the return-value prose is a bonus rather than a necessity, and no prerequisite an agent needs in order to call it is missing.

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 define the single parameter, and it does fully: optional, "YYYY-MM-DD" format, defaults to today, and critically it only affects which day's VO2 max is read. It also preempts a semantic ambiguity by noting that Garmin's 'heart rate threshold' and 'lactate threshold' are the same value.

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 and resource (get current running fitness/threshold snapshot) and enumerates the three data sections it returns: lactate threshold, VO2 max, race predictions. The word 'current' plus 'always return Garmin's latest available values' implicitly separates it from history-oriented siblings like get_threshold_history, but it never names any sibling explicitly.

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?

Gives clear selection context with 'Answers "where is my fitness right now?" in one call', framing it as the snapshot tool. It does not, however, tell the agent when to prefer get_running_threshold or get_threshold_history instead, so the routing guidance against the closest alternatives is missing.

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

Deploy Server

Other Tools