Skip to main content
Glama
WebCake Storefront MCP

WebCake Storefront MCP

by vuluu2k

page_element

Search, inspect, update, or batch-edit elements in a saved storefront page, or append a new section, with optional dry-run previews before applying changes.

Instructions

Read and edit single elements on a saved page, or append a section. Pick the operation with action and pass that action's arguments (help:true returns its full documentation and schema).

  • search_page_elements: Search/filter elements within a page source.

  • get_page_element: Get full detail of a single element by its ID (e.g.

  • update_page_element: Update properties of a specific element in page source.

  • update_page_elements: Batch update multiple elements in one page.

  • add_section: Append a section to an EXISTING page's source.

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": "page_element"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoFilter by element ID substring (e.g. [search_page_elements]
helpNoReturn the action's full documentation and argument schema instead of running it
textNoFilter by text content substring [search_page_elements]
typeNoFilter by element type (e.g. [search_page_elements]
limitNoMax results (default 50) [search_page_elements]
styleNoStyle to merge, camelCase like the editor (e.g. [update_page_element]
actionYesWhich operation to run
configNoConfig to merge (layout: widthUnit auto|px|%, constraintX/Y, columnStart…). [update_page_element]
eventsNoComplete events array (replaces existing) [update_page_element]
dry_runNoPreview only (true) or apply changes (false). [update_page_element, update_page_elements, add_section]
page_idNoPage ID
sectionNoA section node (from new_section) — object or JSON string [add_section]
updatesNoArray of element updates [update_page_elements]
bindingsNoComplete bindings array (replaces existing) [update_page_element]
has_bindNoOnly elements with data bindings (product, category, blog) [search_page_elements]
specialsNoSpecials to merge (text, custom_class, custom_css, etc.) [update_page_element]
templateNoInsert a library section instead (ids from list_section_templates) [add_section]
element_idNoElement ID (e.g. [get_page_element, update_page_element]
has_eventsNoOnly elements with events (click, submit, mouseenter, etc.) [search_page_elements]
responsiveNoResponsive breakpoint overrides (e.g. [update_page_element]
allow_shrinkNoAllow the source to shrink by more than half: set it when native elements replaced an oversized e… [update_page_element, update_page_elements]
custom_classNoFilter by custom class substring [search_page_elements]
has_custom_classNoOnly elements that have a custom class [search_page_elements]

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.8.0

TDQS

B3.3/5.0
Behavior3/5

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

Annotations only declare readOnlyHint=false, which is consistent with the description's 'Read and edit' framing — no contradiction. The description adds one real constraint beyond the schema: `add_section` appends to an EXISTING page's source. But it says nothing about whether updates are reversible, whether dry_run is recommended, permission requirements, or what each action returns, which matters for a 23-parameter mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The lead sentence is well front-loaded and the bullet list is scannable, but several bullets are visibly truncated mid-phrase ('Get full detail of a single element by its ID (e.g.'), leaving broken fragments that cost more in confusion than they save in length. The list also has no visual hierarchy between read actions and mutating actions.

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 23-parameter, enum-dispatched tool with nested objects and no output schema, the description covers the action surface but omits the shape of composite inputs (`updates` array entries, `section` object) and any return-value expectations. The `help:true` pointer partially compensates, but the agent still cannot call the mutating actions correctly from this text alone.

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 100%, and the schema itself already tags each parameter with the action it belongs to (e.g. '[search_page_elements]', '[update_page_element]'), so the description's bullet list largely restates structured data. The one addition is the `help:true` convention for retrieving per-action schemas, which is genuinely beyond the schema. Baseline 3 is appropriate.

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?

Opens with a specific verb+resource statement ('Read and edit single elements on a saved page, or append a section') and enumerates the five dispatched actions, so an agent knows this is a polymorphic page-element tool. It does not distinguish itself from plausible siblings such as `page`, `build_page`, or `page_draft`, so the reader cannot tell from the text alone why this tool rather than those.

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?

Tells the agent to select behavior via `action` and to pass 'that action's arguments', and flags that `help:true` returns the action's own documentation — a useful escape hatch. However, no guidance is given on action sequencing (e.g. search before get/update) or on when `add_section` should be used rather than `build_page`/`page_draft`. Usage is implied by the action names rather than stated as rules.

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