Skip to main content
Glama

AINDEX

Stop an agent now

stop_agent
Idempotent

Stop an agent at once: nothing runs, nothing waiting is kept, and its open orders on Lighter are cancelled. Positions and their stops stay as they are, unless closePositions is true (every position closed at market, which needs a key that may act). Works with any access key: stopping is always allowed. resume_agent brings it back.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "agent": "<agent>"
    },
    "name": "stop_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentYes
closePositionsNoAlso close every position at market on Lighter.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations by spelling out what is destroyed (nothing running, nothing waiting kept, open orders cancelled), what is preserved (positions and their stops), and the exact opt-in that changes that (closePositions). It also discloses the authorization model ('works with any access key') and the recovery path (resume_agent), which annotations like idempotentHint cannot express.

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

Conciseness4/5

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

Front-loaded with the action and its effects, then the preservation/opt-in caveat, then permissions, then the recovery pointer — a sensible order. Slightly dense with stacked parentheticals ('every position closed at market, which needs a key that may act'), but no sentence is filler.

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

Completeness5/5

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

For a two-parameter mutation tool with no output schema, it covers everything an agent needs before calling: side effects, what survives, the destructive opt-in and its auth requirement, and how to undo. Nothing material is left to inference.

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 50% (only closePositions is described), so the description carries real weight. It explains that closePositions closes every position at market and adds the permission nuance that this 'needs a key that may act', which the schema does not convey. The agent identifier parameter gets no extra explanation, but its regex pattern makes the format self-evident.

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') and immediately enumerates the concrete effects: running work stops, queued work is discarded, and open Lighter orders are cancelled. It also names the inverse sibling (resume_agent), so an agent can distinguish this from resume_agent or set_agent_mode without opening a schema.

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

Usage Guidelines4/5

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

Gives clear conditions for calling it ('at once', 'stopping is always allowed' with any access key) and points to resume_agent as the way back. It does not explicitly state when NOT to use it (e.g., preferring a graceful mode change via set_agent_mode before a hard stop), so it falls short of full when/when-not/alternatives coverage.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources