mcp-creatio

Refresh the feature-toggle cache

refresh-feature-cache

Idempotent

Reloads Creatio feature-toggle states for all users so permission changes take effect. Use after creating, updating, or deleting Feature and AdminUnitFeatureState records.

Instructions

Make Creatio re-read feature-toggle states for all users. set-feature-state already does this; use it after changing Feature / AdminUnitFeatureState rows with create / update / delete. See get-guide: feature-toggle-guide.

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": "refresh-feature-cache"
  }
}

Input Schema

Name	Required	Description	Default
`featureCode`	No	Feature code to refresh (e.g. "FreedomUIComposableApp"); omit to refresh all features.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.8.0Oct 25, 2026

changedInput schema / properties / featureCode / description

Previous value: -"Optional feature code (e.g., \"FreedomUIComposableApp\"). When provided, only that feature's cache is invalidated for all users. Omit to clear the cache for every feature."New value: +"Feature code to refresh (e.g. \"FreedomUIComposableApp\"); omit to refresh all features."

First observedv0.6.5Jun 28, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already cover mutation, idempotency and non-destructiveness, and the description adds context: this is a cache re-read affecting all users, and the underlying guide is referenced. It does not discuss cost or timing of the refresh, which matters for a cache operation.

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?

Three short sentences, front-loaded with the action, followed by the alternative and the prerequisite. No filler, though the 'set-feature-state already does this' aside could make an agent question whether to call this tool at all.

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?

With one optional parameter, no output schema and adequate annotations, the description supplies the missing operational context (when to invoke, related guide). Only minor gaps remain, such as the effect scope and any latency expectations.

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 description coverage is 100% and the single optional featureCode parameter is fully documented there, including the omit-to-refresh-all behavior. The description adds no parameter-level detail beyond that, so the baseline of 3 applies.

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 concrete verb+resource: make Creatio re-read feature-toggle states. It also contrasts itself with set-feature-state, which makes the boundary clear. The phrase 'for all users' slightly muddies the scope, since the schema shows the refresh can be scoped to a single feature code.

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 a clear trigger: call it after changing Feature / AdminUnitFeatureState rows via create / update / delete. It also names the alternative (set-feature-state) that performs the same refresh as a side effect. It stops short of saying when NOT to call it.

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