Skip to main content
Glama

Import: Add Products

create_pre_publish_products

[Import List Product] [What it does] Turns one to 10 supplier products into editable pre-publish products (the items on the DSers Import List page). [When to use] Use it when the user has picked products to import, and whenever the agent needs pre-publish products to exist before editing or publishing them. Trigger words: import this product, add to import list, save it for editing, bulk import. [When not to use] To edit an imported product, use update_pre_publish_product_content. For prices, use update_pre_publish_product_price. To list products in a store, use publish_products_to_stores. [How to use]

  • Send every product in items, including a single product. Each supplier_platform_id and supplier_product_id pair must come from the same search_supplier_products result.

  • Each item's languages is merged with the account's Product Settings languages and saved back: English is always included and counts toward the plan's language limit, and that settings change persists even if the import later fails.

  • When an item's country is omitted the previously selected import country applies, falling back to US; if the setting cannot be read the call stops without writing anything.

  • Read imported_items and failed_items item by item because a batch can partially succeed. Both result types include supplier IDs, and each request item appears in exactly one result array. A missing upstream outcome is reported as UPSTREAM_RESULT_MISSING; verify with list_pre_publish_products before retrying.

  • Do not auto-retry failures; check the reason first, such as a product that already has a pre-publish record.

  • Import List products, draft products, and pre-publish products are the same objects; when users use the old menu wording, proceed normally and answer in generic product terms rather than sending them to a page. [Side effects] Creates pre-publish products and may change account language settings. [Confirmation] Required but skippable; disclose the language-setting change.

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": {
      "items": "<items>"
    },
    "name": "create_pre_publish_products"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemsYesOne to 10 supplier products to add. Use one item for a single-product import. Paste JSON example: [{"country":"US","languages":["EN"],"supplier_platform_id":"159831080","supplier_product_id":"10050011958743969"},{"country":"US","languages":["EN"],"supplier_platform_id":"159831080","supplier_product_id":"10050011958743970"}].

Output Schema

NameRequiredDescriptionDefault
failed_itemsYesSupplier products that were not created and their upstream reasons
imported_itemsYesSupplier products successfully created in the import list
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

A4.6/5.0
Behavior4/5

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

Annotations already declare non-read-only, non-destructive, non-idempotent, closed-world, so the bar is lower, yet the description adds real substance: a persistent account language-settings side effect that survives import failure, a confirmation requirement, partial-success batching, and a no-auto-retry rule with the specific UPSTREAM_RESULT_MISSING code. It does not cover rate limits or what the created record's defaults look like, which keeps it short of a 5.

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?

Front-loaded with bold bracketed section headers (What it does, When to use, When not to use, How to use, Side effects, Confirmation) that make it skimmable despite its length. A few bullets, such as the Import List / draft / pre-publish alias note, are longer than strictly necessary, but no sentence 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 non-idempotent batch mutation with destructive side effects on account settings, the description covers preconditions, per-item result bookkeeping, error codes, and recovery guidance. An output schema exists, so return values are already structured, yet the description usefully flags that each request item lands in exactly one of imported_items or failed_items.

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; the description still adds a cross-parameter constraint not expressible in the schema — each supplier_platform_id/supplier_product_id pair must originate from the same search_supplier_products result. It also reinforces that a single product must still be sent inside items, a usage rule rather than a type rule.

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: turns 1-10 supplier products into editable pre-publish products on the Import List page. It explicitly distinguishes itself from update_pre_publish_product_content, update_pre_publish_product_price, and publish_products_to_stores, so the agent can route without opening sibling schemas.

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?

Contains dedicated 'When to use' and 'When not to use' sections plus trigger phrases (import this product, add to import list, bulk import). Alternatives are named with the condition that selects each one, and the alias note about Import List / draft / pre-publish products resolves a naming ambiguity the agent would otherwise hit.

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.