Skip to main content
Glama

garmin_sync_healthkit

Copy weigh-ins bridged from Apple Health into Garmin Connect, skipping duplicates by timestamp and refusing implausible values. Preview first with a dry run.

Instructions

Copy weigh-ins bridged from Apple Health into Garmin Connect.

Use this when the measurement came from a scale that is NOT bound to Mi Fitness but whose app writes to Apple Health. Not every app does: 蚂蚁阿福 writes nothing at all, which is what the README's Step 0 check exists for. Requires the one-time iPhone Shortcut described in the README's "Apple Health bridge" section; the file it appends to is the only input.

The same guarantees as garmin_sync_weight: every weighing becomes its own entry with the time it was taken (a morning and an evening weighing are two measurements, not one), a weighing Garmin already holds — same moment within three minutes — is skipped so re-runs write nothing, implausible weights are refused rather than written, writes are paced, and each write is confirmed by reading the day back. The only lines folded together are the scale's double upload, a weight-only row followed seconds later by the full one. verified: false entries raise the same timezone-mismatch warning.

THIS WRITES TO YOUR GARMIN ACCOUNT unless dry_run is true. Call with dry_run=true first when the user has not seen the numbers yet.

Args: days: How far back to look, in days. Defaults to 30, capped at 90. dry_run: Report what would be written without writing anything.

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": "garmin_sync_healthkit"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNo
dry_runNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.10

TDQS

A4.3/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden, and it does most of the work: it declares the write semantics in caps, idempotency (same moment within three minutes is skipped, so re-runs are no-ops), refusal of implausible weights, paced writes, and read-back verification. It does not describe the response payload or the format of the input file, leaving the agent to infer what a call returns or how failures surface.

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?

Purpose is front-loaded in one sentence and the critical write warning is capitalized and set apart. Some prose is discursive (README step references, the Chinese app name, the morning/evening illustration), though each sentence does encode a distinct rule rather than padding.

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 mutation tool with no annotations and no output schema, the definition covers the input source, prerequisites, idempotency, safety posture, and dry-run protocol. The remaining gap is return-value shape and the meaning of `verified: false` lines, which are referenced as if the file format were already known.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

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 for both parameters: `days` is scope of lookback with a cap of 90 that the schema does not encode, and `dry_run` is defined as report-without-writing plus a recommended call order. It stops short of saying what an out-of-range `days` does or what the dry-run output contains.

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?

Opens with a specific verb+resource+scope: "Copy weigh-ins bridged from Apple Health into Garmin Connect." It also names the adjacent sibling ("The same guarantees as `garmin_sync_weight`") and states the source condition that selects this tool over it, so an agent can discriminate without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit when-to-use rule ("a scale that is NOT bound to Mi Fitness but whose app writes to Apple Health"), an explicit exclusion (apps that write nothing at all), a hard prerequisite (one-time iPhone Shortcut, README's Apple Health bridge), and a sequencing rule ("Call with `dry_run=true` first when the user has not seen the numbers yet"). That is about as complete as guidance gets.

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