This record as markdown: /tools/openclaw/instructions.md
What instructions does on OpenClaw
AI agents call instructions to retrieve information from OpenClaw without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why instructions is rated Low
The name and description suggest this tool retrieves or provides instructions/guidance text (likely configuration or compaction instructions), which is a read operation. However, the description is minimal and uninformative, reducing confidence. 'Compaction' could relate to data compaction operations, but without more context the most reasonable interpretation is that this tool reads/fetches instructional content.
From the tool's definition Tool name: 'instructions', description: 'Extra compaction instructions'
Attacks that exploit this kind of access
The rule that runs instructions safely
PolicyLayer is an MCP gateway: it sits between your AI agents and OpenClaw, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For instructions, this is the rule to start with:
instructions is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect OpenClaw, apply this rule, and every instructions call is checked against it from then on.
Questions about instructions
Extra compaction instructions. It is categorised as a Read tool in the OpenClaw MCP Server, which means it retrieves data without modifying state.
Register the OpenClaw MCP server in PolicyLayer and add a rule for instructions: 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 OpenClaw. Nothing to install.
instructions 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 instructions 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 instructions. 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.
instructions is provided by the OpenClaw MCP server (openclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on OpenClaw, and thousands of servers like it.
This server
Across the catalogue