Skip to main content
Glama

Start an experiment

start_experiment
Idempotent

Start a draft: from now on its arms are served to the users who pass its targeting. Refused when another test is running or paused on the same surface and placement. 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": "start_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?

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false) it discloses the actual state transition, a conflict rule tied to surface+placement, and an authorization gate on MCP writes. Those are exactly the operational facts an agent needs before mutating state and are not derivable from the structured fields.

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 short sentences, each earning its place: effect, refusal condition, precondition. The consequence is front-loaded and nothing is repeated.

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 mutation tool with annotations and one required id, the description covers effect, conflicts, and permission gating, which is most of what matters. With no output schema it could still say what is returned (e.g. the updated experiment or a refusal error shape), leaving a small gap.

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?

Schema coverage is 100% and the single id parameter is already documented as 'Experiment id, from list_experiments', so the description adds nothing about the parameter. Baseline 3 applies when the schema carries the full burden.

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 ('Start a draft') and immediately defines the observable consequence: its arms are served to users passing its targeting. That distinguishes it cleanly from pause_experiment, resume_experiment, stop_experiment and create_experiment without needing the sibling list.

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 explicit when-not conditions ('Refused when another test is running or paused on the same surface and placement') and a hard prerequisite ('Only works when the app allows MCP writes'). It stops short of naming the alternative tool to use when the precondition fails, so it is strong but not fully routing.

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