MyDesigns

Deep search designs

deep_search_designs

Deep search, the app's Scout AI: MyDesigns researches what really sells for one or more niches on Amazon right now and makes designs from each, each with a title, description and tags. It is heavy research that takes a few minutes, so do your own research and use create_products by default; offer deep search only when the seller wants to know what sells or wants ideas from real sales data, tell them it uses up to 1.5 AI credits per design, and start it only after they agree. Needs a Pro plan or higher. Put the search terms that share a folder and instructions in one call, one per line: they run as one job, like the Scout AI page. Terms for another folder or with other instructions, such as another store's, go in a call of their own: start them all right away, without waiting for the first to finish, and each returns its own jobId. Then check each with get_deep_search_results and the jobId returned here, show the seller the designs, and make products from the ones they pick with create_products and their designIds.

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": {
      "niche": "<niche>",
      "count": "<count>"
    },
    "name": "deep_search_designs"
  }
}

Input Schema

Name	Required	Description	Default
`count`	Yes	How many designs to make for each search term, 1 to 10.
`niche`	Yes	The search terms, in the seller's words, one per line and up to 20, e.g. "funny nurse" or "funny nurse\nfishing dad".
`folderId`	No	The folder id from list_folders that the designs go in. Leave it out for the seller's first folder.
`productType`	No	The kind of product the designs are for: standard_tshirt (default), premium_tshirt, pullover_hoodie, crewneck_sweatshirt, long_sleeve, tank_top, mug, tumbler, tote_bag, throw_pillow, paper_poster, canvas_wall_art, iphone_case, ornament, and more.	standard_tshirt
`instructions`	No	The seller's own instructions for how every design looks, in their words, as on the Scout AI page, e.g. "light colored text and elements, so they stand out on black shirts". Leave it out when the seller gave none.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only declare write/openWorld/non-idempotent; the description adds the operationally decisive facts: multi-minute runtime, up to 1.5 AI credits per design, Pro-plan requirement, consent requirement, and asynchronous job semantics where each call returns its own jobId and calls should be fired without waiting. That is exactly the context annotations cannot convey.

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 and the default/alternative split are front-loaded, and nearly every clause carries operational weight (cost, plan, consent, job grouping, follow-up). It is a dense run-on paragraph that re-states some schema content ('one per line', 'in their words'), so it is slightly longer than needed but not padded.

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 costly, slow, non-idempotent, open-world generation tool with no output schema, the description covers prerequisites, cost, consent, batching, the returned jobId, the retrieval step, and the downstream product creation. Nothing an agent needs to invoke or follow up correctly 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 batching semantics not expressed in the schema: terms sharing a folder and instructions belong in one call and run as a single job, while terms for another folder or with other instructions require separate calls fired concurrently. That grouping rule meaningfully changes how niche, folderId, and instructions get combined.

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?

Names the specific capability ('researches what really sells for one or more niches on Amazon right now and makes designs'), the artifacts produced (title, description, tags), and explicitly contrasts it with create_products and create_designs as the default path. An agent can distinguish it from every sibling without opening a 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?

States the default ('do your own research and use create_products by default'), the exact trigger for offering this tool ('only when the seller wants to know what sells or wants ideas from real sales data'), a consent gate ('start it only after they agree'), and a plan prerequisite (Pro or higher). It also prescribes the post-call workflow via get_deep_search_results and create_products.

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

All MyDesigns 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?