Self-critique the generated copy system against conversion heuristics. Scores across 7 categories: Clarity (25%), Persuasion Framework (20%), Behavioral Design (15%), Voice & Tone (15%), Microcopy (10%), Specificity (10%), SEO (5%). Returns weighted score with verdict: SHIP (4.0+), REVISE (3.0-3....
AI agents call copy_critique to retrieve information from RC Engine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and evaluates an existing artifact (COPY-SYSTEM.md), computes a weighted score, and returns a verdict. It performs analysis and retrieval only, with no side effects, data modification, or execution of external operations. Misuse potential is minimal — it can only return scoring/feedback.
From the tool's definition Self-critique the generated copy system against conversion heuristics. Scores across 7 categories... Returns weighted score with verdict
Attacks that exploit this kind of access
Self-critique the generated copy system against conversion heuristics. Scores across 7 categories: Clarity (25%), Persuasion Framework (20%), Behavioral Design (15%), Voice & Tone (15%), Microcopy (10%), Specificity (10%), SEO (5%). Returns weighted score with verdict: SHIP (4.0+), REVISE (3.0-3.9), or REWRITE (<3.0). Call AFTER copy_generate. Loads the COPY-SYSTEM.md artifact automatically. It is categorised as a Read tool in the RC Engine MCP Server, which means it retrieves data without modifying state.
Register the RC Engine MCP server in PolicyLayer and add a rule for copy_critique: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches RC Engine. Nothing to install.
copy_critique is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the copy_critique rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for copy_critique. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
copy_critique is provided by the RC Engine MCP server (originalrashmi/rc-engine-product-framework). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →