SplitLaunch

experiments_create

Create a draft external URL A/B test and return the created experiment. Use controlUrl and variationUrl for the two destinations, trafficAllocation for the variation share, targeting for optional filters, and experiments_set_status after user approval to launch.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	Yes
`projectId`	No	Optional project ID. Omit only when the API key is project-scoped or the account has a clear default project.
`targeting`	No	Optional targeting object. Device and visitor targeting are available on all plans; trafficFilters and geoFilters require Plus or Pro. Use documented pixel metadata keys such as utm_source, utm_medium, utm_campaign, device, browser, or geo fields.
`controlUrl`	Yes	Existing customer-owned URL for the control experience.
`variationUrl`	Yes	Existing customer-owned URL for the variation experience.
`urlPatternRules`	No	Optional Pro-only URL pattern rules for advanced matching across multiple paths. Prefer simple controlUrl/variationUrl first.
`trafficAllocation`	No	Traffic sent to the variation. Accepts 0-1 or 0-100; default is 50%.
`preserveRedirectParams`	No	Default: true.

TDQS

A3.8/5.0

Behavior3/5

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

The description discloses that the experiment is created as a draft and that a separate call to set_status is needed to launch. Annotations already indicate a non-read-only, non-destructive operation. The description adds the draft lifecycle context but omits details on authorization requirements or side effects beyond creation.

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 description is a single sentence that efficiently conveys the tool's purpose and key parameters without unnecessary words. It is well-structured for quick comprehension, though slightly dense.

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

Completeness3/5

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

For a tool with 8 parameters, nested objects, and no output schema, the description provides minimal guidance on the return value (only 'return the created experiment'). It lacks details on error cases, authentication, or what fields the returned experiment contains, leaving gaps for the agent.

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 high (88%), and the description mostly paraphrases the schema (e.g., 'use controlUrl and variationUrl for the two destinations'). It does not add significant new meaning beyond what the schema already provides, so the baseline score 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 description clearly states the tool creates a draft external URL A/B test and returns the experiment. It specifies the resource ('experiment') and the action ('create'), and distinguishes from sibling tools like experiments_update or experiments_set_status by noting the draft nature and subsequent approval step.

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?

The description provides clear context on when to use this tool (to create a draft experiment) and mentions the follow-up step of using experiments_set_status after approval. While it does not explicitly exclude alternative tools, it effectively guides the agent on the creation workflow.

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

All SplitLaunch tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0

Disambiguation5/5

Each tool targets a distinct resource and action combination (e.g., domains_add, experiments_create, goals_deactivate, reports_experiment_chart). There is no overlap or ambiguity; even the three report tools serve clearly different purposes (totals, time-series, channel breakdown).

Naming Consistency4/5

The vast majority of tools follow a resource_action snake_case pattern (domains_add, experiments_list). A couple deviate (billing_portal, usage_summary) but still place the resource first, making the pattern predictable and easy to parse.

Tool Count5/5

With 23 tools covering projects, domains, experiments, goals, reports, billing, health, and usage, the count is well-scoped for a split-testing platform. Each tool addresses a specific need without ballooning into excessive granularity.

Completeness4/5

The tool surface provides CRUD-like operations for core entities (projects, experiments, goals, domains) and essential report types. Minor gaps exist (no goal update tool, no experiment delete—only archive) but these are reasonable trade-offs for the domain.

Resources

Need Help?