Skip to main content
Glama
Sign In

AgentX

by com.agentxhq
OverviewDiscussionsAdmin

interrupt_agent

Idempotent

Stop an agent that is working right now, so it puts down what it is doing and listens. Use this when an agent has gone the wrong way and you want to redirect it — follow with send_message to give it new direction. Name the agent as list_agents shows it, and pass chat when stopping by agent name. session_id targets one exact session and does not take chat.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "interrupt_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoSame as agent. agent wins when both are set.
chatNoChat id for stopping by agent name (the `bubble_id` from `create_chat` or `list_chats`). Required when stopping by agent name; not used with session_id.
agentNoName of the agent to stop, as shown by `list_agents`.
session_idNoStop one exact running session instead of naming an agent. Only use this when you already have a session id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true, so the safety profile is covered. The description adds real behavioral context — the agent halts current work and awaits input, and interruption is meant to be followed by a redirect message. It does not say what happens to in-flight/partial work or whether the stopped agent can resume, which is the main remaining gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the action, then the usage rationale, then parameter routing. No filler, and each sentence carries distinct information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-optional-parameter, non-destructive control tool with no output schema, the description covers action, motivation, sequencing, and parameter routing. The only omission is the fate of the interrupted agent's partial work or return behavior, a minor gap given annotations already signal a safe, idempotent operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds cross-parameter routing rules — agent name comes from list_agents, chat accompanies an agent-name stop, and session_id targets one session and must not be paired with chat. Some of this restates the schema's chat/session_id descriptions, which limits it to a 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Stop an agent") plus a temporal scope ("that is working right now"), which distinguishes it from siblings like send_message, wait, and check_agent_output. The phrase "puts down what it is doing and listens" clarifies the effect beyond a bare "stop".

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit when-to-use condition ("when an agent has gone the wrong way and you want to redirect it") and names the follow-up action (send_message) so the agent knows this tool is a step in a sequence, not a terminal action. It also explains the parameter-selection rule: name the agent plus chat, or use session_id alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All AgentX toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources