Skip to main content
Glama

editDashboard

Change a Garmin dashboard page's layout, custom widgets, or language texts; call writeDashboard first. Run with no arguments to inspect the current layout, widget catalogue, and missing translations.

Instructions

Changes the layout, the custom widgets or the languages of the dashboard page (a page from the template; call writeDashboard first). Without arguments it only reads: the reply has the layout, the custom widgets, the missing texts of each language, the catalogue of built-in widgets and widgetApi, the guide to writing a custom widget. layout replaces the whole layout (the text of the page's 'Copy layout'); place adds widgets at the end of a board; widgets adds or replaces custom widgets by id and saves them in the widget library (/widgets.json), which every page from the template gets; removeWidgets removes them from this page and its boards, forgetWidgets also from the library. widgetTexts adds texts to custom widgets by id, language and key, e.g. {"longest-ride": {"de": {"title": "Längste Fahrt"}}}. languages adds page texts by key, e.g. {"de": {"title": "Training + Erholung"}}: keys and {placeholders} as in englishTexts: true; a text with "|" has a singular and a plural form. Missing texts show in English. removeLanguages removes languages that languages added.

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": "editDashboard"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoThe .html file; relative paths are inside the data dir
placeNo
layoutNoA whole layout: { base, boards: { all: [{ id, widget, type?, span, hidden?, baseSpan? }] }, seen?: { all: [widget names] } }. `seen` is the record of the preset widgets that each board has met: give it back as you got it.
widgetsNo
languagesNoTexts by language code and key
widgetTextsNoTexts of custom widgets by widget id, language code and key
englishTextsNoAlso return the English texts to translate
forgetWidgetsNoIds of custom widgets to remove from the library and from this page
removeWidgetsNoIds of custom widgets to remove from this page
removeLanguagesNoCodes of added languages, e.g. de

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.13.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full disclosure burden and does well: it flags the read-only no-argument behavior and its return contents, states that `layout` replaces the whole layout, and reveals a cross-page side effect (custom widgets saved to <data-dir>/widgets.json so every page from the template gets them). It does not cover error behavior, permissions, or atomicity of multi-field calls.

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-loads the read/write distinction and the writeDashboard prerequisite before enumerating parameters, so it is well ordered. The semicolon-chained parameter catalogue is dense and demands careful parsing, but nearly every clause carries information for a 10-parameter tool.

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?

Given 10 parameters, nested objects, and no output schema, the description covers the read-mode reply contents and the persistence semantics of each mutation, which is close to complete. It leaves open whether `path` is effectively required and whether multiple mutation parameters can be combined in one call.

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 coverage is 80%, so the baseline is 3, but the description genuinely adds meaning: `place` appends at the end of a board, `removeWidgets` versus `forgetWidgets` differ in library scope, `languages` uses '|' for singular/plural and {placeholders}, and missing texts fall back to English. Some of the text restates schema descriptions verbatim, which holds it back from a 5.

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?

Names a specific verb+resource ('Changes the layout, the custom widgets or the languages of the dashboard page') and immediately scopes it as a template page tool that depends on writeDashboard. It also carves out the no-argument read mode, so an agent knows this is a dual read/write tool rather than a pure editor.

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 an explicit prerequisite ('call writeDashboard first') and a per-mode trigger for each parameter group, which is stronger guidance than most schemas provide. It stops short of naming when to prefer a sibling for plain reading, so the read path is left to inference.

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