AI agents use describe to create or update resources in Jj — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Jj environment.
This tool modifies metadata (description/commit message) for a revision. It's a reversible write operation - the description can be changed again. It does not delete data or execute code, making Write the appropriate category.
From the tool's definition Update the change description or other metadata for a revision
Attacks that exploit this kind of access
Update the change description or other metadata for a revision in a Jujutsu (jj) repository. By default, targets the working-copy revision (. It is categorised as a Write tool in the Jj MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Jj MCP server in PolicyLayer and add a rule for describe: 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 Jj. Nothing to install.
describe is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the describe 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 describe. 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.
describe is provided by the Jj MCP server (jj-mcp-server). 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 →