Digital Maker AI

make_website

MAKES a Shopify store theme (ZIP) for selling digital products, from the user's Website Maker allowance (Free 3 for life, Pro 5, Premium and Ultimate 10 a month). In Claude and ChatGPT do not collect these answers in chat: call open_product_maker with product website and the panel collects them and calls this itself. Elsewhere follow the website's order (see open_product_maker). Step 4 is required: the user needs a Shopify account and should sign up through the link open_product_maker gives; only pass shopify_ready true after the user has said in their own words that their Shopify account is ready. About a minute; answers with a job id for check_product. The user uploads the ZIP in Shopify > Online Store > Themes > Add theme > Upload zip file.

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": {
      "product_types": "<product_types>",
      "shopify_ready": "<shopify_ready>"
    },
    "name": "make_website"
  }
}

Input Schema

Name	Required	Description
`colour`	No
`details`	No	Optional: anything specific about the products.
`audience`	No	Who the store is for.
`store_name`	No
`product_types`	Yes	What the store sells, 1 to 4.
`shopify_ready`	Yes	True only after the user confirmed their Shopify account is set up.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 7, 2026

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the quota model (Free 3 for life, Pro 5, Premium/Ultimate 10 per month), the ~1 minute duration, and that it is asynchronous, returning a job id for check_product. Gaps remain on what happens if the allowance is exhausted or the job fails, and whether the ZIP link expires.

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?

Purpose is front-loaded and every sentence carries operational information, but the single dense paragraph bundles quota, routing, prerequisite and upload steps, and the dangling reference to "Step 4" is opaque without the steps it indexes.

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 6-parameter, no-annotation, no-output-schema tool, the definition covers async behavior, next-step routing, the mandatory Shopify prerequisite, and post-generation user instructions. It is close to complete, with only failure/quota-exhaustion behavior and the meaning of the unmentioned optional fields left unaddressed.

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 coverage is 67%, so baseline is 3. The description adds real meaning for shopify_ready (only true after the user states in their own words that the account is ready) and explains that the panel, not the chat, collects the answers, but store_name, audience, details and the colour enum are left entirely to the schema.

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?

"MAKES a Shopify store theme (ZIP) for selling digital products" gives a specific verb, a specific artifact, and a concrete output format, and the allowance framing separates it from generic creation siblings like make_ebook or make_spreadsheet.

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

Usage Guidelines5/5

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

It routes explicitly: in Claude/ChatGPT, do NOT collect answers in chat but call open_product_maker, which calls this itself; elsewhere follow the website's order. It also states the prerequisite chain (Shopify account, sign up via the link) and the exact condition for passing shopify_ready=true.

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

All Digital Maker AI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?