Skip to main content
Glama
WebCake Storefront MCP

WebCake Storefront MCP

by vuluu2k

page_draft

Destructive

Build storefront pages section by section in a local draft, then commit incrementally to avoid timeouts. Inspect, list, or clear drafts before publishing.

Instructions

Build a page section by section in a draft, then commit it as one save. Pick the operation with action and pass that action's arguments (help:true returns its full documentation and schema).

  • start_page_draft: Start a page draft (no network).

  • add_draft_section: Append ONE section to a local page draft (NO network — this is the durable per-section cache step that can't time out).

  • get_page_draft: Inspect a local page draft: its meta, the section ids, total section count, and (if a commit is in progress) the page_id + committed_count.

  • list_page_drafts: List local page drafts for the current site (summaries only: id, name, slug, type, section count, commit progress, updated_at).

  • commit_page_draft: Persist a local page draft to the backend INCREMENTALLY (one section per request, 120s timeout each) so no single huge request can time out.

  • clear_page_draft: Delete a local page draft (does NOT delete any backend page already created from it).

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_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
seoNoSEO for this page → settings.seo (applied on commit). [start_page_draft]
helpNoReturn the action's full documentation and argument schema instead of running it
nameNoPage name [start_page_draft]
slugNoURL slug WITHOUT a leading slash, e.g. [start_page_draft]
typeNoPage kind. SPECIAL pages need a site data-source enabled on commit: store→use_store, member→use_m… [start_page_draft]
actionYesWhich operation to run
dry_runNoValidate+preview only (true) or create+persist incrementally (false) [commit_page_draft]
sectionNoA section node (from new_section) — object or JSON string [add_draft_section]
draft_idNoDraft id from start_page_draft [add_draft_section, get_page_draft, commit_page_draft, clear_page_draft]
is_homepageNoSet as the site homepage on commit [start_page_draft]

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.8.0

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true, and the description adds genuinely useful behavior beyond them: commit is incremental at one section per request with a 120s timeout each, start/add are network-free, and `clear_page_draft` explicitly does NOT delete an already-committed backend page — which is the key scoping fact for a destructive tool. It does not disclose what a commit or start call returns, nor failure/retry behavior when a mid-commit section fails, so it stops short of full behavioral disclosure.

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

Conciseness5/5

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

Front-loads the overall two-phase model in one sentence, then uses a tight bullet per action with no repeated boilerplate. Every line carries distinct information (network vs local, timeout behavior, deletion scope), and nothing is padded.

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 10-parameter action-dispatch tool with nested objects and no output schema, the description covers the workflow, the per-action roles, and even the return shape of `get_page_draft` (meta, section ids, count, page_id, committed_count). What is left is the return/error contract for `commit_page_draft` and `start_page_draft`, which an agent would want given there is no output schema.

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%, so the baseline is 3, but the description adds real meaning on top: it explains that action-specific arguments are passed alongside `action` and that `help:true` returns the full documentation and argument schema for that action, which a reader of the flat schema would not infer. Per-action parameter ownership is still mostly carried by the schema's bracketed tags rather than the prose.

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?

Opens with a specific verb-and-resource model ("Build a page section by section in a draft, then commit it as one save") and then enumerates every action the `action` enum dispatches to, each with a concrete verb and object (start/add/get/list/commit/clear a page draft). An agent can distinguish the sub-operations from each other and from the sibling `page`/`build_page` tools without opening the schema.

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 strong per-action usage context: `add_draft_section` is flagged as the durable, no-network cache step that can't time out, `commit_page_draft` is described as the incremental persist path, and `dry_run` is implied as the validation-only route. The one gap is that it never says when to choose this draft workflow over the sibling `page` or `build_page` tools.

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