Get the input schema for one or more tools. It is a good idea to call this tool first to understand how to successfully call execute_tool.
AI agents call describe_tool_input to retrieve information from Latitude Sh MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries schema information—a read-only operation with no side effects. It helps users understand how to call other tools but does not itself create, modify, delete, or execute anything. The blast radius is minimal since misuse would only return informational schema data.
From the tool's definition Tool name 'describe_tool_input' and description 'Get the input schema for one or more tools' indicate retrieval of metadata about tool schemas without modifying, deleting, or executing infrastructure.
Attacks that exploit this kind of access
Get the input schema for one or more tools. It is a good idea to call this tool first to understand how to successfully call execute_tool. It is categorised as a Read tool in the Latitude Sh MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Latitude Sh MCP Server MCP server in PolicyLayer and add a rule for describe_tool_input: 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 Latitude Sh MCP Server. Nothing to install.
describe_tool_input 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_input 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_input. 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_input is provided by the Latitude Sh MCP Server MCP server (latitudesh/latitudesh-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 →