Skip to main content
Glama
brilliant-directories-mcp

brilliant-directories-mcp

Official

refreshSiteCache

Clears the site's internal template, theme, widget, menu, and page caches when recent admin edits aren't appearing on the public site. Target one cache area or refresh all.

Instructions

Refresh the site cache (template/theme/widget/menu/page invalidation) - Clears BD's internal template/theme/widget caches. Useful when recent admin edits to design settings or widgets aren't showing on the public site yet.

Use when: the user has just updated a template, theme setting, widget, menu, or page layout and the public site is still serving the old version. Also a safe troubleshooting step if they report a recent admin-edit not appearing after ~1 minute.

Optional parameters:

  • scope - target one cache area only (data_widgets, settings, web_pages, css, menus, sidebars). Faster than a full refresh. Omit to refresh all 6.

  • full=1 - include heavier db_optimization + file_permissions passes in addition to the 6 core areas. Slower; use only when the user reports persistent issues and lighter refreshes didn't help.

Not needed after createWebPage / updateWebPage / createWidget / updateWidget — those tools auto-refresh and return auto_cache_refreshed: true in the response, or auto_cache_refresh: "scheduled" when the refresh is queued to run shortly together with other writes (normal; it runs on its own). Only call manually if a write returned auto_cache_refreshed: false (check auto_cache_refresh_error for the cause).

Do NOT use for:

  • Routine workflow noise - do not call after every bulk op on non-page resources. Most BD writes unrelated to pages are live immediately; cache invalidation is a targeted fallback, not a default post-step.

Returns: { status: "success", message: "Cache refreshed successfully", areas_refreshed: [...], scope: "full", full: false }. The areas_refreshed array lists exactly what was cleared - useful for logging or reporting back to the user. Example default response:

{
  "status": "success",
  "message": "Cache refreshed successfully",
  "areas_refreshed": ["data_widgets", "settings", "web_pages", "css", "menus", "sidebars"],
  "scope": "full",
  "full": false
}

With full=1 the areas_refreshed additionally includes db_optimization and file_permissions. Invalid scope values return an error listing the valid set: { status: "error", message: "Invalid scope value: <x>. Valid values: ..." }.

Undocumented by BD publicly; exposed via admin API-permissions UI.

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": "refreshSiteCache"
  }
}

Input Schema

NameRequiredDescriptionDefault
fullNoPass 1 to also run db_optimization + file_permissions refresh (heavier, slower). Pass 0 or omit for standard refresh of the 6 core areas only.
scopeNoTarget a specific cache area instead of refreshing all 6. Omit to refresh all. Valid values: data_widgets, settings, web_pages, css, menus, sidebars. Invalid scope returns an error listing the valid set.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv6.55.39
  2. Removedv6.55.19
  3. Addedv6.49.4
  4. Removedv6.48.1
  5. Addedv6.0.19
  6. Removedv6.0.18
  7. Addedv6.0.7
  8. Removed
  9. First observedv1.0.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare the mutation/safety profile; the description adds the operational behavior that matters: that most writes auto-refresh, what the 'scheduled' refresh means, that full=1 runs extra db_optimization and file_permissions passes and is slower, and what an invalid scope returns. Nothing here contradicts readOnlyHint=false or destructiveHint=false.

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-loaded with the core action, then clearly sectioned with bold headers for use-when, parameters, exclusions, and returns. Slightly verbose in the returns section, where a prose sentence, a full example JSON block, and an enumeration of areas_refreshed repeat the same information.

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?

There is no output schema, and the description fully carries that burden by documenting the response shape, the areas_refreshed array, the full=1 additions, and the error case. For a two-parameter mutation tool with no required params, an agent has everything needed to call it correctly.

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 100%, so baseline is 3; the description goes further by explaining the trade-off between scoped and full refresh ('faster than a full refresh') and the escalating condition for full=1 ('only when persistent issues and lighter refreshes didn't help'). It adds decision guidance the enum descriptions alone do not.

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 (refresh) and resource (site cache) and immediately enumerates what is invalidated (template/theme/widget/menu/page). It also names the sibling write tools (createWebPage, updateWebPage, createWidget, updateWidget) whose writes already trigger this behavior, so an agent can tell it apart without opening schemas.

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?

Gives explicit when-to-use (recent design/widget edit not appearing after ~1 minute), when-not-to-use (routine post-bulk-op noise, most non-page writes are live immediately), and a concrete precondition for calling manually (only if a write returned auto_cache_refreshed: false). Alternatives are named rather than implied.

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