Skip to main content
Glama

Supplier: Get Product Ideas

list_featured_product_collections
Read-onlyIdempotent

[Supply Product] [What it does] Lists curated product collections visible to the account's supplier applications: collection names, descriptions and scene types. Theme entry points only, never product records. [When to use] Call it when the merchant gives no category or keyword and asks what to sell, what is recommended, or what is selling well; the agent also calls it first when a supplier product search needs a direction. Trigger words: product ideas, best sellers, what should I sell, curated collections, inspiration. [When not to use] With a clear category or keyword, use search_supplier_products for products and prices and get_supplier_product for one product; use create_pre_publish_products to import, and list_managed_store_products for the merchant's own listings. [How to use]

  • Collections are editorial placements, not a sales ranking, and the scene type is not a product category: present them as curated themes and use the type for grouping only.

  • Collection IDs are banner identifiers, not product IDs; never pass them to a product lookup, and show the name and description instead.

  • An empty list is a valid result, not a failure: say no themes are available and stop; do not retry or re-tune parameters.

  • To limit platforms, copy supplier platform IDs only from list_stores supplier_apps[].supplier_platform_id; omit them when unsure to cover every visible platform. [Side effects] Read-only; no data or configuration is changed. [Confirmation] None required. [Follow-up] Themes only: once the merchant picks a collection, search it with search_supplier_products; listing themes alone does not answer "what should I sell".

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": "list_featured_product_collections"
  }
}

Input Schema

NameRequiredDescriptionDefault
supplier_platform_idsNoOptional supplier platform IDs to intersect with visible supplier apps. Copy exact values from list_stores supplier_apps[].supplier_platform_id. Paste JSON example: ["100000001"].

Output Schema

NameRequiredDescriptionDefault
ideasYesAll visible product-idea scenes matching the requested supplier applications
matched_countYesNumber of visible scenes returned
toolcall_response_atYesUTC timestamp when the Tool response was returned, formatted as RFC3339.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is low, yet the description still adds substantive behavior: an empty list is a valid success state with an explicit 'do not retry' instruction, collection IDs are banner identifiers that must never be passed to product lookups, and no confirmation is required. The follow-up section also closes the loop that listing themes alone does not answer 'what should I sell.'

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?

Bracketed section headers front-load what it does, when to use, and when not to use, so an agent can stop reading early. It is on the long side and the trigger-word list is somewhat redundant with the when-to-use sentence, but no section is filler.

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 one-optional-parameter read tool with an output schema and full annotations, everything an agent needs is present: scope, routing, ID-handling pitfalls, empty-result handling, and the required next step. Nothing material is left to guesswork.

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?

With a single optional parameter at 100% schema coverage, the baseline is 3; the description goes beyond the schema by naming the authoritative source for values (list_stores supplier_apps[].supplier_platform_id) and stating the default behavior when omitted — cover every visible platform. It does not restate the format or maxItems, but that is already in 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 specific verb and resource ('Lists curated product collections visible to the account's supplier applications') and immediately scopes it with 'Theme entry points only, never product records,' which is the single most important disambiguation for an agent that might otherwise expect products.

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?

Explicit when-to-use ('merchant gives no category or keyword and asks what to sell') with trigger words, plus a when-not-to-use block that routes to named alternatives: search_supplier_products, get_supplier_product, create_pre_publish_products, list_managed_store_products. Conditions that select each alternative are stated rather than inferred.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.