Skip to main content
Glama

Stop an experiment

stop_experiment
DestructiveIdempotent

Stop a running or paused test for good without rolling anything out: everyone gets the live config again. It can't be restarted. Rolling out a winner is done by a person in the dashboard. Only works when the app allows MCP writes.

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": {
      "id": "<id>"
    },
    "name": "stop_experiment"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesExperiment id, from list_experiments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

The annotations already flag destructiveHint=true and idempotentHint=true, and the description adds substance beyond them: the stop is irreversible, nothing is rolled out, all users fall back to the live config, and the operation is gated on MCP write permission for the app. The permission and irreversibility disclosures are exactly what an agent needs before a destructive mutation.

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?

Four short sentences, front-loaded with the outcome, then irreversibility, then the alternative path, then the permission gate. Nothing is repeated or padded.

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 single-argument destructive mutation with no output schema, the definition covers consequences, irreversibility, permission requirements, and where the id comes from. The only remaining gap is what the call returns or how it behaves on an already-concluded experiment, which is minor.

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

Parameters3/5

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

There is a single parameter at 100% schema description coverage, and the schema already explains the id comes from list_experiments. The description adds no further detail about the id (format, scope, or whether an already-stopped experiment errors), so the baseline 3 applies.

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?

The definition pairs a specific verb ('Stop') with a precise resource ('a running or paused test') and immediately states the outcome semantics: no rollout, everyone reverts to live config. The phrase 'for good' and 'It can't be restarted' lets an agent distinguish this from pause/resume siblings without opening their schemas.

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?

It gives clear conditions for use (a test that is running or paused), an exclusion with a named alternative channel ('Rolling out a winner is done by a person in the dashboard'), and a precondition ('Only works when the app allows MCP writes'). It stops short of naming pause_experiment or resume_experiment as the reversible alternatives, but the irreversible/reversible contrast is clear.

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