Skip to main content
Glama

Shipfound

by co.shipfound.api
OverviewDiscussionsAdmin

Set up an App Store A/B test

app_experiment_create

Set up a product page test as a draft: up to 3 treatments, each a set of new captioned screenshots, against the current product page, for a share of visitors (trafficProportion, percent). Apple tests the icon, screenshots and previews only, not text, for up to 90 days. The founder starts it from the results app (or App Store Connect); never say it is running before they do. Growth. Free.

Input Schema

NameRequiredDescriptionDefault
nameYes
appIdNo
localeNoDefault en-US
treatmentsYes
trafficProportionNoPercent of product page visitors in the test; default 50

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / treatments / items / properties / screenshots / items / properties / proof
      Added value: +{
+  "const": "rating",
+  "description": "A proof line with the app's own App Store rating, filled from the public listing; refused under 4.5 stars or 20 ratings",
+  "type": "string"
+}
  2. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare a non-destructive mutation (readOnlyHint=false, destructiveHint=false). The description adds that it creates a draft (not a running test), limits Apple's testing to icon/screenshots/previews, and states the founder must start it—valuable behavioral context beyond annotations.

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 front-loaded with the action and constraints; four sentences each add relevant details. The final 'Growth. Free.' is a bit terse but likely categorizes the tool. No major waste.

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 complex mutation with nested objects and no output schema, the description covers draft status, what Apple tests, duration, and who launches it. It leaves some parameter explanation to the schema, but annotations cover the safety profile.

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 40%, so description should compensate. It only partially does: it mentions treatments (up to 3, captioned screenshots) and trafficProportion, but omits name, appId, and locale. The schema already provides descriptions for some fields.

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 states a specific verb ('Set up'), resource ('product page test'), and scope ('as a draft', 'up to 3 treatments'). It distinguishes from sibling 'app_experiment_list' by focusing on creation of an App Store A/B test.

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 context for use (product page test, up to 90 days) and a crucial usage rule ('The founder starts it... never say it is running'). However, it does not explicitly name when to use this over 'experiment_create' or other experiment tools.

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

All Shipfound toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources