Skip to main content
Glama
splithub-io

SplitHub

Official

splithub_create_experiment

Create A/B experiments for React and Next.js apps; this legacy alias forwards to splithub_experiment_create for the current create action.

Instructions

Old name of splithub_experiment_create, kept for one release: call splithub_experiment_create instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesexperiment key, lowercase
toNoredirect experiments: variant → destination path
endNoISO date the experiment ends
goalNothe goal: any event name the app sends with track() (signup, Video Played) or a goal key from the config; an event not in goals becomes a goal, nothing to declare first
kindYes
nameNohuman name shown instead of the key; can be renamed later, the key stays
layerNomutual exclusion: experiments in one layer never share a visitor; bucket ranges [start, end) must not overlap
matchNoredirect experiments: the path it runs on, e.g. /
startNoISO date the experiment starts
statusNo
valuesNovalue experiments: variant → value
factorsNomvt only: factor → level → value, e.g. { headline: { old: "Old", new: "New" }, button: { blue: "#2563eb", green: "#16a34a" } }; first level = control; at most 4 factors × 4 levels
minDaysNoopt-in fewest days before a verdict (default 0 = none); verdicts otherwise depend on sample size
trafficNopercent of visitors in the experiment (default 100)
weightsNorelative weights, same order as variants (not for mvt)
variantsNovariant keys, first = control (not for mvt)
secondaryNogoals (event names or goal keys) to watch next to the primary goal
goodSampleNototal visitors at which verdict.sample.quality turns good (default 5000); informational, never changes the verdict
guardrailsNogoals (event names or goal keys) that must not get worse; { goal, worse: "higher" } when a rise is bad (refunds, errors). A breach makes the verdict guardrail_breached: do not ship
descriptionNo
maxVisitorsNostop counting after this many visitors

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior3/5

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

With no annotations and 21 parameters, the description carries the whole disclosure burden. It usefully discloses the deprecation window ('kept for one release'), but doesn't say whether calls still succeed, whether they behave identically to the replacement, or whether a deprecation warning is returned.

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?

One sentence, zero waste, front-loads the identity ('old name of...') before the redirect. Ideal shape for a deprecation notice.

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 deprecated alias with a richly documented schema and no output schema, the description is sufficient: it identifies the tool and redirects. A note on whether the alias is byte-for-byte equivalent to the replacement would make it complete.

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 86%, so the schema already explains nearly all 21 parameters in detail. The description adds nothing parameter-specific, which is acceptable for a pure deprecation stub where the caller should be using the replacement anyway.

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

Purpose4/5

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

The description states exactly what this tool is (a deprecated alias of splithub_experiment_create) and names the replacement sibling, so an agent can route away from it immediately. It stops short of restating the underlying operation (creating an experiment), but the sibling name conveys it.

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?

Explicit and unambiguous: 'call splithub_experiment_create instead' tells the agent precisely when not to use this tool and which alternative to pick. No inference required.

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