Skip to main content
Glama

shopify_create_menu

DestructiveIdempotent

Create storefront navigation menus with up to three nested levels, linking to collections, products, pages, or catalogs. Verifies the complete menu tree before confirming creation.

Instructions

Create a storefront navigation menu (e.g. a 'main-menu' replacement or a footer menu) with at most three item levels. The connector independently reads back and compares the complete tree before success. Requires the online-store-navigation scopes; a connection without them returns SHOPIFY_NAVIGATION_SCOPE_REQUIRED (offer a Shopify reconnect).

Args:
    title (required): Menu title shown in the admin (e.g. 'Main menu').
    handle (required): Menu handle referenced by the theme (e.g. 'main-menu', 'footer').
    items (required): JSON-string list of menu items: [{title, type?, url?, resource_id?, items?}]. type defaults to HTTP (a plain link); use COLLECTION/PRODUCT/PAGE/CATALOG with resource_id (a GID) to link store resources. Nested items may be at most three levels deep.
    project_id: Authenticated Project UUID.
    project_ref: Exact project correlation reference.
    connector_account_ref: Project-bound connector account alias.
    idempotency_key: Stable business-action identity.
    effect: Claimed read or write effect; Spring verifies it.
    approval_ref: Approved platform task UUID when resuming a write.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
itemsNo
titleNo
effectNo
handleNo
project_idNo
project_refNo
approval_refNo
idempotency_keyNo
connector_account_refNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Addedv0.1.1

TDQS

A4.1/5.0
Behavior4/5

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

Beyond the annotations (write/read-only, idempotent, destructive, open-world), the description adds useful operational detail: it 'independently reads back and compares the complete tree before success', names the exact scope-error code, and explains idempotency/effect/approval fields. It does not elaborate on what destructiveHint means for an existing handle, but it does not contradict the 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 opening sentence front-loads the purpose and key constraint, followed by scopes/error behavior and an organized Args block. The text is dense but each line earns its place; only minor ambiguity like 'JSON-string list' keeps it from being maximally clean.

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?

The description covers the operation, the required scope, failure behavior, read-back verification, and every parameter's meaning, which is substantial given the schema provides no descriptions. It does not state what happens when the given handle already exists or whether the menu is replaced, which would be useful given the destructiveHint and the 'main-menu replacement' example.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema description coverage at 0%, the description carries the parameter burden and explains all nine arguments, including the item shape with type defaults and examples. However, it marks title/handle/items as required while the schema makes all properties nullable/optional, and 'items' is described as a 'JSON-string list' while the schema types it as an array of strings—a meaningful mismatch an agent could trip on.

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 opens with a specific verb+resource: 'Create a storefront navigation menu', adds concrete examples ('main-menu' replacement or footer menu), and states the at-most-three-level constraint. This makes it distinguishable from sibling tools like shopify_update_menu, shopify_delete_menu, and shopify_get_menu without needing to inspect those tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage through 'Create' and examples, and it gives prerequisite guidance ('Requires the online-store-navigation scopes... offer a Shopify reconnect'). However, it never explicitly says when to prefer this over shopify_update_menu or shopify_delete_menu, nor does it state when-not-to-use, so alternative-routing guidance is left to inference.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/RPasquale/lightbulb-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server