Skip to main content
Glama
brilliant-directories-mcp

brilliant-directories-mcp

Official

getWidget

Read-onlyIdempotent

Fetch a single Brilliant Directories widget by ID or name to read its metadata or HTML, CSS, and JavaScript source for editing or auditing. Code fields stay stripped unless include_code=1 is set.

Instructions

Get a single widget - Fetch a single widget record by widget_id. Read-only.

Lean-by-default keep-list: returns only widget_id, widget_name, widget_type, short_code, date_updated, revision_timestamp, is_default. The code fields (widget_data, widget_style, widget_javascript) are stripped — restore with include_code=1.

Use when: you have a widget_id (from listWidgets or admin) and want the widget's SOURCE code to edit or audit. To preview the rendered widget on the front-end, embed it on a page as <div>[widget=Name]</div> and view the page.

Required: widget_id or widget_name.

See also: listWidgets (enumerate), updateWidget (modify).

Returns: { status: "success", message: [{...record}] } - the message array contains 1 record with all widget fields (widget_data = HTML, widget_style = CSS, widget_javascript = JS, plus metadata).

For the full field list, see listWidgets.

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": "getWidget"
  }
}

Input Schema

NameRequiredDescriptionDefault
widget_idNo
widget_nameNoInstead of widget_id: the exact name. Returns the site's copy, else BD's widget.
include_codeNoOpt in to return `widget_data`, `widget_style`, `widget_javascript` (the HTML/CSS/JS). Default stripped. Needed before `updateWidget` edits to the code.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv6.59.638
    • addedInput schema / properties / widget_name
      Added value: +{
      +  "description": "Instead of widget_id: the exact name. Returns the site's copy, else BD's widget.",
      +  "type": "string"
      +}
    • removedInput schema / required
      Removed value: -[
      -  "widget_id"
      -]
  2. Changed1 schema field changedv6.58.0
    • addedInput schema / properties / include_code
      Added value: +{
      +  "default": 0,
      +  "description": "Opt in to return `widget_data`, `widget_style`, `widget_javascript` (the HTML/CSS/JS). Default stripped. Needed before `updateWidget` edits to the code.",
      +  "enum": [
      +    0,
      +    1
      +  ],
      +  "type": "integer"
      +}
  3. Addedv6.55.39
  4. Removedv6.55.19
  5. Addedv6.49.4
  6. Removedv6.48.1
  7. Addedv6.0.19
  8. Removedv6.0.18
  9. Addedv6.0.7
  10. Removed
  11. First observedv1.0.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, so safety is covered; the description adds real value beyond that by disclosing the lean-by-default field keep-list, exactly which fields are stripped, and how to restore them with include_code=1. It also states the response envelope (`{status, message:[...]}`) since no output schema exists. Minor weakness: it later says the message array contains 'all widget fields,' which sits awkwardly against the lean keep-list.

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?

Bolded section headers and front-loaded verb make it scannable, and most sentences (keep-list, use-when, see-also) earn their place. It runs longer than a single-record getter needs, and the closing 'Returns' paragraph partly restates the keep-list while contradicting it with 'all widget fields.'

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and only 67% parameter coverage, the description carries the return shape, the stripped-field behavior, the required-argument rule, and sibling routing — everything an agent needs to call this correctly. The only residue is the small internal ambiguity about whether the record is full or lean by default.

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 67% and the schema already documents widget_name and include_code well, so the baseline would be a 3. The description earns above that by supplying a constraint absent from the schema itself: '**Required:** `widget_id` or `widget_name`' — important given the schema lists 0 required parameters — and by tying include_code to the concrete code fields and the updateWidget workflow.

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 ('Fetch a single widget record by `widget_id`') and immediately differentiates from siblings via the 'See also' line naming listWidgets (enumerate) and updateWidget (modify). An agent can distinguish this from the list/create/delete/render variants 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?

Explicit 'Use when' condition (you have a widget_id from listWidgets or admin and want source code to edit or audit) plus an explicit when-not route for previewing the rendered widget (embed `<div>[widget=Name]</div>` on a page). It also names the alternative tools and their roles, leaving nothing to inference.

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

Deploy Server

Other Tools