Digital Maker AI

find_digital_stores

Read-onlyIdempotent

STORE FINDER: real online stores that sell digital products (ebooks, digital planners, spreadsheets, Notion templates, presets, workbooks, journals, templates), with estimated monthly revenue, active products, average price, the channels they market on (Meta ads, Google ads, YouTube) and whether they blog. Use it for questions like "show me a digital product store that sells digital planners making over $5k a month" or "which spreadsheet stores run Facebook ads". Answer from this data, not from memory. It also covers the ebook stores sold from AI avatar YouTube channels (Bertha, Elias Yoder, Silas Mercer and others): set ai_avatar_only for those, and each comes with the channel that sells it. Call it ONCE per answer. To compare product types or answer "what are the best digital products to sell", use digital_product_trends instead: never call this once per category. In Claude and ChatGPT it shows the stores as cards in a panel; say one short sentence about what was found. Costs nothing. Revenue and product numbers are on Pro and above; Free sees the stores only. Revenue is an estimate.

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": "find_digital_stores"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Default 8.
`channel`	No	Only stores marketing on this channel.
`keyword`	No	A word to match in the store name, domain, product focus or the YouTube channel that sells it, e.g. "budget", "wedding" or "bertha".
`sort_by`	No	Default revenue (highest first).
`category`	No	What the store mainly sells.
`has_blog`	No	Only stores with a blog.
`max_revenue`	No	Maximum estimated monthly revenue in US dollars.
`min_revenue`	No	Minimum estimated monthly revenue in US dollars, e.g. 5000.
`ai_avatar_only`	No	Only stores sold from AI avatar YouTube channels (mostly single ebooks, buyers come from the videos).

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 8, 2026

addedInput schema / properties / ai_avatar_only

Added value: +{
+  "description": "Only stores sold from AI avatar YouTube channels (mostly single ebooks, buyers come from the videos).",
+  "type": "boolean"
+}

changedInput schema / properties / keyword / description

Previous value: -"A word to match in the store name, domain or the niche it was found for, e.g. \"budget\" or \"wedding\"."New value: +"A word to match in the store name, domain, product focus or the YouTube channel that sells it, e.g. \"budget\", \"wedding\" or \"bertha\"."

AddedNov 7, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only declare read-only/idempotent/non-destructive; the description adds material context beyond them: plan gating (Free sees stores only, revenue and product counts require Pro), the caveat that revenue is an estimate, that the call costs nothing, that results render as cards in a Claude/ChatGPT panel and should be followed by one short sentence, and the instruction to answer from the data rather than memory. These are behavioral facts an agent cannot derive from the schema.

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 with purpose and returned fields, but the text then sprawls into a long run-on that mixes usage rules, UI rendering, pricing tiers and estimate caveats, with some redundancy ('use digital_product_trends instead: never call this once per category') and a chat-product-specific aside about panels. Every element is arguably useful, but ordering and compression could be tighter.

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 read-only search tool with no output schema and full schema coverage, the description covers the decision to call, the alternative to avoid, the Pro-tier visibility limit, and the meaning of the trickiest flag. Nothing an agent needs in order to call it correctly or interpret results is missing.

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: it explains that ai_avatar_only restricts to stores sold from AI avatar YouTube channels and that the selling channel is returned alongside, and it gives a keyword example ('bertha') that ties free-text search to the channel field. The remaining parameters 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?

States a concrete verb and resource ('STORE FINDER: real online stores that sell digital products') and enumerates the returned fields (estimated monthly revenue, active products, average price, marketing channels, blog presence). It explicitly separates itself from the sibling digital_product_trends, so an agent can route between them without opening either schema.

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?

Gives sample user phrasings that should select this tool, names the alternative (digital_product_trends) and the condition that selects it ('what are the best digital products to sell', comparing product types), states the call-frequency rule ('Call it ONCE per answer... never call this once per category'), and explains when to set ai_avatar_only. When-not-to-use is explicit, which is rare.

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?