This record as markdown: /tools/cowork-bench/delete-paragraph.md
What delete_paragraph does on Cowork Bench
AI agents call delete_paragraph to permanently remove resources in Cowork Bench, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why delete_paragraph is rated Critical
This tool permanently removes document content without the ability to undo the operation through the tool itself. Deletion is irreversible and constitutes data destruction. While the impact is scoped to a single paragraph rather than an entire document, the irreversible nature makes it Destructive rather than Write.
From the tool's definition Tool name is 'delete_paragraph' and description states 'Delete a paragraph from a document.' The word 'delete' combined with the action of removing content indicates irreversible data destruction.
Attacks that exploit this kind of access
The rule that runs delete_paragraph safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cowork Bench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For delete_paragraph, this is the rule to start with:
delete_paragraph is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Cowork Bench, apply this rule, and every delete_paragraph call is checked against it from then on.
Questions about delete_paragraph
Delete a paragraph from a document. It is categorised as a Destructive tool in the Cowork Bench MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Cowork Bench MCP server in PolicyLayer and add a rule for delete_paragraph: 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 Cowork Bench. Nothing to install.
delete_paragraph is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_paragraph 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 delete_paragraph. 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.
delete_paragraph is provided by the Cowork Bench MCP server (0717376/cowork_bench). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cowork Bench, and thousands of servers like it.
Across the catalogue