Evaluate an array of content items (headings, prose, CTAs, labels, captions, metrics, outcomes) against UX-writing principles and deterministic heuristics. Returns a per-item verdict (pass/warn/fail) with matched principle ids, concrete issues grounded in principle text, a before→after rewrite su...
AI agents call audit_content to retrieve information from Raven without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
goals | array | — | Optional content goals (e.g. ['clarity','conversion']); recorded for traceability. |
items | array | Yes | Array of content items to audit. |
system | string | — | Optional content-system id (e.g. 'ux-writing'); recorded for traceability. |
Parameters from the server's own tool schema.
This tool retrieves and analyzes content without modifying, deleting, executing code, or triggering external operations. It generates advisory feedback ("before→after rewrite suggestion") but does not apply changes to any data. The scope is strictly informational auditing, making it a Read-category tool with low severity—misuse would at worst generate poor recommendations without irreversible consequences.
From the tool's definition Tool evaluates content against UX-writing principles and returns verdicts, suggestions, and summaries. The description emphasizes it is 'pure offline' with no network access, performs analysis only ("evaluate", "returns", "flags"), and explicitly states no…
Attacks that exploit this kind of access
Evaluate an array of content items (headings, prose, CTAs, labels, captions, metrics, outcomes) against UX-writing principles and deterministic heuristics. Returns a per-item verdict (pass/warn/fail) with matched principle ids, concrete issues grounded in principle text, a before→after rewrite suggestion, and an aggregate summary. Heuristics: metric items must carry a number+unit; cta/label must be action-led and ≤4 words; prose flags passive voice, jargon, and hedging; headings flag filler openers and buzzwords; captions flag duplication of any heading in the batch. Pure offline — no network or browser. Use this instead of evaluate_design when you need per-item content verdicts rather than the principle library. It is categorised as a Read tool in the Raven MCP Server, which means it retrieves data without modifying state.
audit_content accepts 3 parameters: goals, items, system. Required: items. The full parameter table on this page comes from the server's own tool schema.
Register the Raven MCP server in PolicyLayer and add a rule for audit_content: 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 Raven. Nothing to install.
audit_content 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 audit_content 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 audit_content. 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.
audit_content is provided by the Raven MCP server (raven-mcp). 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 →