Skip to main content
Glama
WebCake Storefront MCP

WebCake Storefront MCP

by vuluu2k

compose

Read-only

Build structurally valid page elements, sections, rows, and page skeletons from the builder factory instead of hand-writing nodes for storefront page assembly.

Instructions

Create element nodes from the factory (never hand-write nodes). Pick the operation with action and pass that action's arguments (help:true returns its full documentation and schema).

  • new_element: Build a single structurally-valid element node from the real builder factory.

  • new_section: Build a complete section node with children laid out in the builder's vertical grid.

  • new_row: Build a multi-column ROW container: children laid out SIDE BY SIDE (not stacked).

  • new_page_skeleton: Return an empty but valid page source: { sections: [] }. Add sections built with new_section, then save with build_page.

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": {
      "action": "<action>"
    },
    "name": "compose"
  }
}

Input Schema

NameRequiredDescriptionDefault
hugNoContent-sized columns (max-content): a menu, pills, a button group — not cards [new_row]
helpNoReturn the action's full documentation and argument schema instead of running it
optsNoFactory opts: { text, src, width, height, style, config, specials, events, bindings, responsive, … [new_element]
typeNoElement type (see list_elements) [new_element]
actionYesWhich operation to run
row_gapNoVertical gap (px) between wrapped rows (default 24) [new_row]
childrenNoChild element specs, stacked vertically in the section [new_section, new_row]
collapseNoColumns to show per breakpoint, e.g. [new_row]
col_widthsNoExplicit per-column unit objects (length = #children), e.g. [new_row]
column_gapNoHorizontal gap (px) between columns (default 24) [new_row]
section_optsNoOptional factory opts for the section node itself [new_section]
container_optsNoOptional factory opts for the row container node itself (e.g. [new_row]

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.8.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations declare readOnlyHint=true, and the description is consistent with that: these are factory constructors that return nodes, with persistence deferred to build_page. Beyond the annotations it discloses the help:true escape hatch and the concrete return of new_page_skeleton ({ sections: [] }). It does not state return shape for the other three actions.

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?

Front-loaded one-sentence rule followed by a scannable per-action bullet list; each bullet carries distinct information about output or layout. Slight redundancy between the parenthetical help note and the schema's help description, but nothing padding.

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 12-parameter tool with nested objects and no output schema, the description covers action selection well and points to help:true for full docs. However, it never describes the return value of new_element/new_section/new_row, which is the main gap when no output schema exists.

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?

Schema coverage is 100% and action-tagged, so the baseline is 3. The description goes past it by explaining what each `action` enum value actually produces, which the schema only labels as 'Which operation to run', and by explaining the help:true parameter's behavior rather than just its type.

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 opens with a specific verb+resource ('Create element nodes from the factory') despite the opaque tool name 'compose', and the bullet list distinguishes the four operations precisely (element vs section vs side-by-side row vs page skeleton). It also names build_page as the subsequent save step, though it does not differentiate from sibling page_element.

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?

Gives a clear directive ('never hand-write nodes') and an explicit procedural path: pick an action, pass that action's args, then save with build_page. The new_row vs new_section distinction (side by side vs stacked) is exactly the kind of routing guidance needed. Lacks explicit when-not/exclusion guidance against sibling element tools.

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