describe_tools

Get full parameter schemas and examples for tools. Omit names to list all tools.

Server Mementos @hasna/mementos
Category Read
Risk class Low
Parameters 00 required

What describe_tools does on Mementos

AI agents call describe_tools to retrieve information from Mementos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why describe_tools needs a policy

This tool retrieves metadata about available tools and their schemas. It does not create, modify, delete, or execute anything—it only returns information about the tool interface itself. This is a classic Read operation with minimal risk (low severity) and high confidence given the explicit description.

From the tool's definition Tool name 'describe_tools' and description 'Get full parameter schemas and examples for tools' indicate a retrieval operation.

Questions about describe_tools

What does the describe_tools tool do? +

Get full parameter schemas and examples for tools. Omit names to list all tools. It is categorised as a Read tool in the Mementos MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on describe_tools? +

Register the Mementos MCP server in PolicyLayer and add a rule for describe_tools: 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 Mementos. Nothing to install.

What risk level is describe_tools? +

describe_tools is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit describe_tools? +

Yes. Add a rate_limit block to the describe_tools 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.

How do I block describe_tools completely? +

Set action: deny in the PolicyLayer policy for describe_tools. 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.

What MCP server provides describe_tools? +

describe_tools is provided by the Mementos MCP server (@hasna/mementos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.