Skip to main content
Glama

getDashboardData

Retrieves consolidated Garmin training dashboard data—HR zones, fitness age, recent and prior activities, HRV, sleep, readiness, weekly digest, and units—in one call.

Instructions

All the data of the training dashboard in one call: HR zones, fitness age, the activities of the last weeks weeks (compact summaries, with strength sets and laps where they apply; a strength session with sets also has planVerdicts: hit or miss for each exercise of the plan that the watch ran, null without a plan; a run whose laps are read, or whose .FIT file is saved, has planVerdicts too: hit or miss for each lap with a planned target), the activities of the weeks before for the period comparison, daily HRV, the last 14 days of sleep and daily summaries (with recoveryHistory, also short rows of the older days: date, sleep hours, sleep score and resting HR), and units: the measurement system of the Garmin profile (metric, statute_us or statute_uk) that the page shows; the data itself is always metric; locale: the language of the Garmin profile, e.g. it or pt-BR. Keeps a local cache and fetches from Garmin only what is new since the last call, so a rebuild or an update needs few calls. sync in the result says what was fetched: Garmin calls, .FIT files downloaded (fitDownloads) and new activities. digest, first in the result: the server's totals for the whole period and for each Monday-Sunday week (sessions, km, hours, load), the training load of the last 7 and 28 days, best efforts, races and strength top sets, the plan verdicts of the strength sessions done (strengthPlan), the long runs with their half split and HR drift, the longest run and the race predictions (Riegel), the page's readiness verdict for today with its inputs (readiness), and today's fitness, fatigue and form (fitnessFatigue); quote them instead of your own sums. For another date range, use the activities: each one is on its own line. A load is null (n/a) when the sessions have none; estimatedLoads counts the loads that are estimates from heart rate. A week with partial: true starts before the period. Without HRV and sleep data the digest has no readiness: give the verdict as n/a. The full result is large: 12 weeks can be about 180 KB, which can be over the tool output limit of the assistant. writeDashboard with preview: true gives only the digest, the activities of each board and the settings.

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": "getDashboardData"
  }
}

Input Schema

NameRequiredDescriptionDefault
weeksNoWeeks to cover, default 12, max 52
workoutsNoAlso the laps of the runs of each run name that repeats, to compare a workout across weeks: the last 8 (downloaded once) and older ones whose .FIT file is saved; default false
recoveryHistoryNoAlso the sleep and resting HR rows of the whole period, not only the last 14 days

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.13.0

TDQS

A3.9/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: local cache with incremental fetch of only new Garmin data, a `sync` block reporting Garmin calls / fitDownloads / new activities, an explicit size warning (12 weeks ≈ 180 KB, over the assistant output limit), null semantics for load and readiness, and `partial: true` week flag. This is behavior an agent could not infer from schema or annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One enormous run-on block with nested parentheses (planVerdicts explained twice, inline before the sentence closes) and no separation between return contents, caching, size limits, and usage advice. Every fact is arguably useful, but the structure actively hinders parsing and the key operational warning about output size is buried mid-paragraph instead of front-loaded.

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?

No output schema exists, and the description compensates by naming most result regions (digest, sync, units, locale, readiness, fitnessFatigue) and their edge cases. A few result fields are only gestured at ('best efforts, races and strength top sets'), which leaves gaps in a very large payload, but the essential calling information is present.

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%, so the schema already documents all three parameters; baseline is 3. The description does add some meaning — `recoveryHistory` returns short rows (date, sleep hours, sleep score, resting HR) and `weeks` drives both the current period and the prior-period comparison — but `workouts` is never explained in the description, so the added value is partial.

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?

Opens with a precise scope statement: 'All the data of the training dashboard in one call', then enumerates the resource contents (HR zones, fitness age, activities, HRV, sleep, daily summaries, digest). The verb is implicit (get) and the enumeration is sprawling, but an agent can tell exactly what this returns versus e.g. getDailySummary or getSleep, which cover only one slice.

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 routing: 'For another date range, use the activities: each one is on its own line' and 'writeDashboard with preview: true gives only the digest...' when the ~180 KB payload would exceed the output limit. It does not systematically state when to prefer the narrower siblings (getHeartRateZones, getSleep) over this aggregate call, so guidance is strong but not exhaustive.

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