Garmin MCP Lite

Overview Schema Source Related Servers Discussions Admin

garmin_add_body_composition

Write a weight or body-composition measurement to Garmin Connect, where it appears in the weight chart. Confirm values before saving because entries cannot be undone through this tool.

Instructions

Write one weight / body-composition measurement to Garmin Connect.

THIS WRITES TO YOUR GARMIN ACCOUNT. Garmin stores it as a FIT body-composition file, the same channel its own Index scale uses, so the entry shows up in the Garmin Connect app's weight chart. Confirm the numbers with the user before calling this: there is no undo through this tool.

Garmin keeps every entry, so calling twice for the same day can leave two weigh-ins. The response includes a warning when the day already had one.

Args: weight: Body weight in KILOGRAMS (e.g. 70.5). Values above 500 are rejected as an accidental gram value. date: When the measurement was taken. YYYY-MM-DD (recorded at 07:00 local) or a full ISO 8601 timestamp. Defaults to now. body_fat: Body fat percentage, e.g. 18.5. body_water: Body water percentage, e.g. 55.2. muscle_mass: Muscle mass in kilograms. bone_mass: Bone mass in kilograms. bmi: Body mass index. Garmin derives this from your profile height when omitted, so leave it out unless you have a reason to override it. basal_met: Basal metabolic rate in kcal/day. metabolic_age: Metabolic age in years.

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": {
      "weight": "<weight>"
    },
    "name": "garmin_add_body_composition"
  }
}

Input Schema

Name	Required	Description	Default
`bmi`	No
`date`	No
`weight`	Yes
`body_fat`	No
`basal_met`	No
`bone_mass`	No
`body_water`	No
`muscle_mass`	No
`metabolic_age`	No

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.1.10Nov 9, 2026

TDQS

A4.5/5.0

Behavior5/5

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

With no annotations present, the description carries the full burden and does so well: it flags the account-level write, that the entry is stored as a FIT file and appears in the Garmin Connect weight chart, that there is no undo through this tool, and that duplicates are possible with a `warning` returned in the response when the day already has an entry. This is exactly the side-effect and idempotency information an agent needs before a mutation.

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 mutation warning and confirmation instruction are front-loaded before the boring details, and the Args block is scannable with one line per parameter. Despite its length, every sentence carries operational value; nothing is 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 9-parameter mutation tool with no annotations and no output schema, the description covers side effects, validation limits, defaults, and even the one meaningful response field (`warning`). The only gap is that it does not say what a successful response otherwise contains, though that is a minor omission given the tool's simplicity.

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% across 9 parameters, so the description must compensate fully, and it does: every parameter gets a unit and example (weight in kg with a 500 upper-bound rejection rule, body fat, body water, muscle/bone mass in kg, BMI with guidance to omit it since Garmin derives it from profile height, basal_met in kcal/day, metabolic_age in years). Date format options and the 07:00-local default are also spelled out.

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 opens with a specific verb and resource: 'Write one weight / body-composition measurement to Garmin Connect.' It also clarifies the storage mechanism (FIT body-composition file) and visibility in the weight chart. It does not explicitly name the read-side sibling garmin_body_composition or garmin_sync_weight, so sibling differentiation is implied by the write verb rather than stated.

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 concrete when-to-use context: confirm numbers with the user first, no undo exists, and calling twice for the same day may create duplicate weigh-ins. It stops short of naming an alternative tool (e.g., the read counterpart for checking existing entries), leaving the agent to infer that step.

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