Skip to main content
Glama
Connect IQ MCP

Connect IQ MCP

by idoo

Sign in to Garmin

auth_login

Signs in to Garmin through a browser, optionally adding Garmin Connect, and waits up to 15 minutes; returns status immediately when saved credentials still work.

Instructions

Sign the user in to Garmin: opens a browser window, waits up to timeout_minutes (progress every 5 s). Returns auth_status at once if credentials still work. connect=true adds Garmin Connect. No secrets returned. One window at a time; 10 min cooldown after one closes unsigned.

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": "auth_login"
  }
}

Input Schema

NameRequiredDescriptionDefault
connectNoalso sign in to Garmin Connect (default false)
timeout_minutesNohow long to wait for the user to finish signing in, 1-15 (default 10)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, non-idempotent), it discloses that a browser window is launched, progress is emitted every 5 s, no secrets are returned, only one window may exist at a time, and a 10-minute cooldown follows an unsigned close. Those operational constraints are exactly the kind of context annotations cannot express; only the failure mode when a second call is attempted mid-window is left 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?

Four short clauses, front-loaded with the action, then the fast path, then the side effects and constraints. No sentence is redundant with the title or schema.

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 an interactive, open-world auth tool with no output schema, the description covers what the agent must anticipate: a blocking wait with a bounded window, an immediate short-circuit, side-effect scope via connect, and cooldown/one-window limits. It could still state what status the call returns on timeout or user cancellation.

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

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both parameters are already described there, so the baseline is 3. The description adds only a marginal detail, that waiting reports progress every 5 s during timeout_minutes, but does not explain what happens when the timeout is exhausted.

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?

States a specific verb and resource ('Sign the user in to Garmin') and immediately describes the observable behavior: browser window opens, waits, returns auth_status if credentials still work. An agent can distinguish this from auth_status (the fast path) without opening either schema.

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 real usage conditions: returns auth_status at once when credentials still work, connect=true additionally signs in to Garmin Connect, and the one-window/10-minute-cooldown constraints tell the agent when a call will fail. It stops short of explicitly naming auth_status as the cheap pre-check alternative, so it is strong but not fully prescriptive.

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