AI agents call describe_tool to retrieve information from Zion without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | Yes |
Parameters from the server's own tool schema.
This is a Read operation: it queries and retrieves information about tool definitions without modifying, executing, or deleting anything. Severity is medium rather than low because the returned schema and descriptions could potentially be used to inform attacks on other tools, but the tool itself performs only harmless data retrieval.
From the tool's definition Tool description states it 'Return[s] the full description, op list, and argument schema' — purely retrieval operations with no side effects. Reads metadata about tools from a catalog.
Attacks that exploit this kind of access
Return the full description, op list, and argument schema for one deferred catalog tool by name (from a search_tools result). Execute it via the resident ztype_tool_calls tool. It is categorised as a Read tool in the Zion MCP Server, which means it retrieves data without modifying state.
describe_tool accepts 1 parameter: name. Required: name. The full parameter table on this page comes from the server's own tool schema.
Register the Zion MCP server in PolicyLayer and add a rule for describe_tool: 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 Zion. Nothing to install.
describe_tool 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 describe_tool 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_tool. 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_tool is provided by the Zion MCP server (zion-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 →