Digital Maker AI

open_product_maker

Read-onlyIdempotent

THE DIGITAL PRODUCT MAKERS: ebook (PDF), digital planner (hyperlinked PDF), spreadsheet template (Excel, opens in Google Sheets) and the Website Maker (a Shopify store theme ZIP for selling digital products). CALL THIS FIRST, straight away, whenever the user asks to make, create or build an ebook, planner, spreadsheet, website, store, Shopify theme or digital product, even with no details: do NOT ask the questions in chat first. Leave product out if they did not say which product, and the panel lets them pick. In Claude and ChatGPT this opens the maker as a panel, like the website, with picture cards for every choice: the user clicks through it and presses the button; after calling, say one short sentence (e.g. that the Website Maker is open below) and do not list or retype the questions. Elsewhere it returns the questions in the website's order: ask them one at a time, then call make_ebook, make_planner, make_spreadsheet or make_website. For the WEBSITE the order is fixed and must be followed: 1 what they sell (1 to 4 types, optional details and store name), 2 who it is for, 3 colour, 4 Shopify account: give them the Shopify sign-up link from this result and wait until they say they have signed up (Basic plan), 5 review, then make_website with shopify_ready true. Costs nothing. Shows how many of each they have left this month.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "open_product_maker"
  }
}

Input Schema

Name	Required	Description
`niche`	No	Prefill: who the planner or the store is for.
`title`	No	Prefill: ebook or planner title.
`topic`	No	Prefill: what the ebook covers, or what the spreadsheet is for.
`colour`	No	Prefill for the website.
`details`	No	Prefill for the website: anything specific about the products.
`product`	No	Leave out when the user did not say which product: the panel shows all four to choose from.
`audience`	No	Prefill for the website: who the store is for.
`store_name`	No	Prefill for the website.
`product_types`	No	Prefill for the website: what the store sells.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedNov 7, 2026

addedInput schema / properties / audience

Added value: +{
+  "description": "Prefill for the website: who the store is for.",
+  "type": "string"
+}

addedInput schema / properties / colour

Added value: +{
+  "description": "Prefill for the website.",
+  "enum": [
+    "blue",
+    "cream",
+    "green",
+    "pink",
+    "black",
+    "teal"
+  ],
+  "type": "string"
+}

addedInput schema / properties / details

Added value: +{
+  "description": "Prefill for the website: anything specific about the products.",
+  "type": "string"
+}

addedInput schema / properties / product / description

Added value: +"Leave out when the user did not say which product: the panel shows all four to choose from."

removedInput schema / required
```
Removed value: -[
-  "product"
-]
```

AddedNov 7, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Beyond the annotations, it discloses channel-dependent behavior (a clickable panel in Claude/ChatGPT versus returning ordered questions elsewhere), the required response style after calling, quota visibility ('how many of each they have left this month'), and that it costs nothing. The readOnlyHint=true annotation is consistent, since the tool only opens a maker or returns questions and defers actual generation to the make_* siblings. Minor gap: no mention of what happens if quota is exhausted.

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 trigger and the panel-vs-questions split are front-loaded, which is good, but the prose is bloated: 'CALL THIS FIRST, straight away', repeated caps, and restated instructions about not retyping the questions. The fixed website step list is valuable but reads as a run-on. It is information-dense yet could be trimmed by a third without losing guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter, zero-required, no-output-schema tool, the description covers everything an agent needs: when to call, what to omit, what happens per client (panel vs. question list), the mandated follow-up call per product, and the fixed Shopify onboarding sequence. Nothing material is left to inference.

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 already 100%, so the baseline is 3; the description adds real meaning by framing every field as optional prefill and by stating that 'product' should be omitted when the user did not specify one so the panel can offer all four choices. It also supplies the fixed website question order (what they sell, who it's for, colour, Shopify account, review), which maps the website-related params into a sequence the schema does not convey.

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?

The description names the resource precisely ('THE DIGITAL PRODUCT MAKERS') and enumerates the four outputs: ebook PDF, hyperlinked planner PDF, Excel/spreadsheet template, and a Shopify theme ZIP via the Website Maker. It also implicitly separates itself from the downstream builders (make_ebook, make_planner, make_spreadsheet, make_website), which it names as the next step rather than as equivalents.

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 gives an explicit trigger ('whenever the user asks to make, create or build an ebook, planner, spreadsheet, website, store, Shopify theme or digital product') plus an explicit exclusion ('even with no details: do NOT ask the questions in chat first'). It also routes to the correct siblings after the intake flow, so an agent knows both when to enter here and where to go next.

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?