Skip to main content
Glama
WebCake Storefront MCP

WebCake Storefront MCP

by vuluu2k

blog

Destructive

Manage storefront articles and categories: list, create, update, delete posts, and organize categories so post-list, grid, and overlay pages have content.

Instructions

Blog articles and blog categories. Pick the operation with action and pass that action's arguments (help:true returns its full documentation and schema).

  • list_articles: List blog articles (metadata only, without HTML content).

  • get_article: Get article details by ID (includes the full HTML content)

  • create_article: Create a blog article so blog/post pages (post-list, grid-blog, post-overlay) have content.

  • update_article: Update a blog article.

  • delete_article: Delete blog articles (soft delete — they disappear from the site)

  • create_blog_category: Create a blog/article category.

  • update_blog_category: Update a blog/article category (name, description, image, slug, SEO).

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": "blog"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoArticle ID [get_article, update_article, delete_article, update_blog_category]
idsNoSeveral article IDs to delete in one call [delete_article]
seoNoSEO settings to change; other existing SEO tags are kept. [update_article, update_blog_category]
helpNoReturn the action's full documentation and argument schema instead of running it
nameNoArticle title [create_article, update_article, create_blog_category, update_blog_category]
pageNoPage number (default 1) [list_articles]
slugNoNew custom slug [update_article, update_blog_category]
tagsNoArticle TAG IDs (uuids from the blog tag list) — not free text [update_article]
termNoSearch articles by title or slug [list_articles]
imageNoHosted image URL [create_blog_category, update_blog_category]
limitNoItems per page (default 20) [list_articles]
actionYesWhich operation to run
imagesNoHosted image URLs; the first is the cover image [create_article, update_article]
contentNoHTML content of the post [create_article, update_article]
summaryNoShort summary / excerpt [create_article, update_article]
is_hiddenNoHide from public [update_article]
category_idNoFilter by blog category id [list_articles]
descriptionNoCategory description [create_blog_category, update_blog_category]
category_idsNoBlog category IDs to file the post under (from create_blog_category) [create_article, update_article]
published_atNoPublish date, ISO/naive datetime (render_inserted_at) [update_article]
remove_category_idsNoBlog category IDs to unfile the post from [update_article]

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.8.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, so the description adds real value beyond them: it discloses that delete is a soft delete whose effect is removal from the site, that list_articles returns metadata without HTML while get_article includes full HTML, and that help:true returns documentation instead of executing. It does not cover permissions, reversibility of deletion, or pagination behavior.

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 dispatch instruction is front-loaded and the per-action bullets are one clean line each, proportionate to seven operations and 21 parameters. A little redundancy remains (the help mechanism appears both in prose and in the schema), but nothing is padded.

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 7-action, 21-parameter mutation surface with no output schema, the description never says which arguments each action actually requires (e.g. what create_article needs beyond a name) and leaves return shape largely to the schema. The help:true escape hatch and the metadata/HTML distinction mitigate this, but it still stops short of fully covering a tool this broad.

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 each parameter is already tagged with the actions it applies to, so the schema carries the semantics. The description's only added parameter meaning is the help:true escape hatch and the metadata-vs-HTML contrast between list_articles and get_article, which is a marginal increment.

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?

Each of the seven actions receives a specific verb+resource line (list/get/create/update/delete articles; create/update blog categories), so an agent knows exactly what the umbrella tool covers. Differentiation from siblings is implicit only through the resource noun 'blog article/category' — nothing explicitly separates it from page, collection, or product 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 tells the agent how to select an operation ('Pick the operation with `action`') and hints at intent for create_article ('so blog/post pages have content'), but gives no when-not guidance and no pointer to alternatives such as api_call for raw/uncatalogued requests. Usage is implied rather than stated.

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