Skip to main content
Glama

Import: Update Organization & Category

update_pre_publish_product_organization

[Import List Product] [What it does] Saves actual Organization, Category, or URL handle changes for one to 100 pre-publish products in one store. [When to use] Use it after get_pre_publish_product_organization has returned the current selections and available Organization and Category choices for the same store so they can be reviewed with the user, and only after the user has chosen concrete listing changes. If the user keeps all current settings, skip this Tool. [When not to use] To read available choices, use get_pre_publish_product_organization. To publish, use publish_products_to_stores. Product content and prices are out of scope. [How to use]

  • Send all selected products in items. Every item requires import_item_id and at least one actual update field: category_ids, organizations, or url_handle.

  • Omitted fields are preserved. Empty category_ids or organizations clears that setting; an empty url_handle clears the handle.

  • Use only field names and value IDs returned for the same store. create_values creates store-level values that may persist if a later product assignment fails.

  • The service serializes writes to the same user and import item, rereads the latest item while holding that lock, applies only supplied fields, and performs read-after-write confirmation.

  • Batches may partially succeed. A successful item returns its IDs and optional created_values; a failed item returns failure_code, failure_reason, failure_hint, and retryable. [Side effects] Changes product store settings and may create store-level Organization values. [Confirmation] Required but skippable; use only values the user explicitly chose.

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": {
      "dsers_store_id": "<dsers_store_id>",
      "items": "<items>"
    },
    "name": "update_pre_publish_product_organization"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemsYesComplete batch of one to 100 selected products for one store. Each entry requires import_item_id and at least one actual update field: category_ids, organizations, or url_handle. Omitted fields are preserved; category_ids=[] clears categories, organizations=[] clears Organization selections, and url_handle="" clears the handle. marketplace_id is category context only and does not count as an update. organizations is a complete replacement list. Do not repeat an import_item_id. Each product has an independent result, so one failure does not cancel the others. Paste JSON example: [{"import_item_id":"123456","url_handle":"my-product"}].
dsers_store_idYesCopy from get_pre_publish_product_organization response. Required.

Output Schema

NameRequiredDescriptionDefault
itemsNoPer-import-item update outcomes when batch items is used
failedNoNumber of batch items that failed
warningsNoNon-blocking mutation warnings
created_valuesNoStore-level organization values created before assignment
dsers_store_idYesUpdated DSers store ID
import_item_idNoUpdated import-list item ID
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 only state readOnly=false, destructive=false, idempotent=false, openWorld=false. The description adds real behavior beyond that: store-level values created via create_values may persist even if a later product assignment fails, writes are serialized per user and item with a reread under lock plus read-after-write confirmation, batches may partially succeed with per-item failure_code/failure_reason/failure_hint/retryable, and confirmation is required but skippable.

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?

The bracketed section headers (What it does, When to use, When not to use, How to use, Side effects, Confirmation) front-load the decision-relevant content and make it scannable. It is long, and some content (partial batch success, omit-to-preserve/empty-to-clear) is restated from the schema descriptions, so it is efficient rather than tight.

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 batched mutation tool with a nested items array and an output schema, the description covers the calling contract, clearing versus preserving semantics, partial-failure return shape, persistence side effects, and the confirmation requirement. Nothing an agent needs to invoke it safely appears to be missing; return values are left to the output schema as expected.

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 cross-field rules the schema does not state as a rule: every item needs import_item_id plus at least one actual update field, marketplace_id is context only and does not count as an update, and organizations is a complete replacement list requiring unchanged selections to be re-sent. That is meaningful semantic lift above the per-field text.

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 a specific verb and resource: saving actual Organization, Category, or URL handle changes for one to 100 pre-publish products in one store. It distinguishes itself immediately from the read sibling (get_pre_publish_product_organization) and from publish_products_to_stores, so an agent can pick the right tool without opening the 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?

It gives explicit ordering (call only after the get tool has returned current selections and available choices), a user precondition (only after the user has chosen concrete listing changes), a skip condition (if the user keeps all current settings, skip), and named alternatives for the read case and the publish case. It also declares out-of-scope domains (content, prices) which map to sibling update tools.

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.