Skip to main content
Glama
Sign In

Marsell

by com.getmarsell
OverviewDiscussionsAdmin

Experiments list

experiments_list
Read-only

Lists the business's tests (A/B experiments): each with its id, name and hypothesis, the variable tested, the surface (paid, organic, email, page), state, variants, who started it, when it started and was decided, and for a decided one its result (the winning variant, its lift, the p value, both samples and the threshold it had to clear). simulated true marks a rehearsal on made-up numbers, which is never evidence. Use it to say what was tested and what won; start a new one with experiment_start, and cite a decided one in learning_write.

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": {
      "state": "<state>"
    },
    "name": "experiments_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
stateYesrunning: still collecting; decided: a winner was called; all: both.
projectNoThe project's id or exact name. Optional when the account has one project.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered; the description adds real value beyond that by explaining that 'simulated true' marks a rehearsal on fabricated numbers and 'is never evidence', which prevents a serious analytical misuse. It does not mention result limits or pagination, which keeps it below the top of the scale.

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?

The lede is front-loaded and the routing sentence at the end earns its place, but the middle is one very long enumeration sentence with stacked parentheticals ('paid, organic, email, page') that is harder to scan than it needs to be. Nothing is outright wasteful, though the field catalogue could have been a tighter list.

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?

With no output schema, the description must carry the return shape, and it does so thoroughly — result fields, lift, p value, samples, threshold, plus the simulated caveat. For a two-parameter read tool the only meaningful gap left is pagination/volume behavior.

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 description coverage is 100% and the enum for state is documented in the schema itself, so the schema carries the parameter burden. The description only implies state filtering through its field list and adds nothing about the optional project parameter; baseline 3 is appropriate.

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 ('Lists the business's tests (A/B experiments)') and immediately enumerates what each record contains, so an agent knows exactly what it gets back. It also names the two adjacent tools (experiment_start, learning_write), making it clearly distinguishable from them.

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 explicit routing: use it to report what was tested and what won, use experiment_start to create a new one, and use learning_write to cite a decided one. This is exactly the when-to-use / when-to-use-something-else guidance that separates selection decisions.

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

All Marsell 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