Skip to main content
Glama
Sign In

Widely

by com.widely-mobile
OverviewDiscussionsAdmin

Set the CRM dashboard

crm_set_dashboard
DestructiveIdempotent

Sets the widgets on the dashboard, which is the first page of My Business. Does not save unless confirm is true. A widget type is count, list, board, or slots. Each widget has a label, an icon from the same list as the menus, and a list name. view is a saved view on that list. slots needs a list that has scheduling. When the card is ready, tell them what you are about to save and ask them to say yes. Use your own words. A yes calls this again with confirm true and the same widgets. Do not call it with confirm true before that yes.

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": {
      "confirm": "<confirm>",
      "widgets": "<widgets>"
    },
    "name": "crm_set_dashboard"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmYesMust be true. A call without confirm true does not save.
widgetsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / widgets / items / properties / icon / description
      Added value: +"Ionicon outline name, such as calendarOutline or peopleOutline. Short names such as calendar, people, list, ticket, cpu, bolt, and shirt are accepted."
    • addedInput schema / properties / widgets / items / properties / icon / enum
      Added value: +[
+  "peopleOutline",
+  "personOutline",
+  "calendarOutline",
+  "timeOutline",
+  "cartOutline",
+  "cubeOutline",
+  "documentTextOutline",
+  "briefcaseOutline",
+  "listOutline",
+  "homeOutline",
+  "cashOutline",
+  "imageOutline",
+  "callOutline",
+  "mailOutline",
+  "pricetagOutline",
+  "constructOutline",
+  "heartOutline",
+  "starOutline",
+  "clipboardOutline",
+  "medkitOutline",
+  "restaurantOutline",
+  "carOutline",
+  "businessOutline",
+  "ribbonOutline",
+  "chatbubblesOutline",
+  "notificationsOutline",
+  "settingsOutline",
+  "gridOutline",
+  "layersOutline",
+  "bookmarkOutline",
+  "flashOutline",
+  "hardwareChipOutline",
+  "receiptOutline",
+  "shirtOutline",
+  "happyOutline",
+  "people",
+  "person",
+  "calendar",
+  "time",
+  "cart",
+  "cube",
+  "documentText",
+  "briefcase",
+  "list",
+  "home",
+  "cash",
+  "image",
+  "call",
+  "mail",
+  "pricetag",
+  "construct",
+  "heart",
+  "star",
+  "clipboard",
+  "medkit",
+  "restaurant",
+  "car",
+  "business",
+  "ribbon",
+  "chatbubbles",
+  "notifications",
+  "settings",
+  "grid",
+  "layers",
+  "bookmark",
+  "flash",
+  "hardwareChip",
+  "receipt",
+  "shirt",
+  "happy",
+  "event",
+  "users",
+  "ticket",
+  "tickets",
+  "cpu",
+  "chip",
+  "bolt",
+  "lightning",
+  "emoji",
+  "smiley"
+]
  2. Added

TDQS

A4.2/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and idempotentHint=true, and the description meaningfully builds on them: 'Does not save unless confirm is true' explains the dry-run/preview semantics that the hints cannot express, and the confirmation protocol explains why re-calling is safe. It also discloses validation constraints (icon must come from the menu icon list, 'slots' requires a scheduling-enabled list, 'view' must be a saved view on that list) that would otherwise only surface as runtime errors.

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?

The purpose and the save-gate are front-loaded, and each short sentence carries a distinct constraint. The confirm rule is stated twice ('Does not save unless confirm is true' and 'Do not call it with confirm true before that yes') and the schema already documents confirm, so there is mild redundancy, though the emphasis is defensible for a destructive operation.

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 two-parameter, no-output-schema mutation tool flagged destructive, the description covers the save gate, the confirmation protocol, and per-widget validation, which is nearly everything an agent needs to call it correctly. The one real gap is what happens to existing dashboard widgets when the new set is applied (replace-all vs merge), which matters given destructiveHint=true.

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 50% and the nested 'type' enum and 'model' field carry no schema descriptions, so the description does real work: it enumerates the widget kinds (count, list, board, slots), explains that 'view' is a saved view on the list, and implies 'model' is the list name. That mapping is left partly implicit ('list name' is never tied to the 'model' key by name), which keeps it below a 5.

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?

States a specific verb and resource ('Sets the widgets on the dashboard') and locates it ('the first page of My Business'), which cleanly separates it from siblings like crm_set_menu, crm_set_navigation, and crm_save_view. It never names an alternative tool, but the resource is unambiguous enough that an agent can pick it without opening a 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 unusually explicit when/when-not guidance for the confirm flow: build the card, tell the user what is about to be saved, wait for a yes, then re-call with confirm true, and never call with confirm true first. It stops short of telling the caller when to prefer this over adjacent configuration tools, so it is strong context but not a full routing rule.

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

All Widely toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources