Skip to main content
Glama

Propose new products

offers_create

[Catalog changes] Before writing titles, descriptions, pictures or attributes call listing_guide (the marketplace's rules and the seller's house rules) and check the draft with listing_check: a draft with a blocking finding is refused here. On Temu: price is the BASE price (what Temu pays the seller), category_id 0 lets Temu choose the category, vat_rate is ignored, and each item needs weight_kg, length_cm, width_cm, height_cm. Propose new products. Simulated first; nothing is sent until the seller approves, and the marketplace reviews each product before it goes on sale. Variants (sizes) of one product are separate items with the same product_main_id. categories_get shows which attributes a category requires and their accepted values. For a whole Shopify catalogue, build a lot with catalog_lot_build and pass lot_id here instead of items. Works on: Demo shop (sample data).

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": "offers_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
skusNoWith lot_id: send only these SKUs of the lot (for a test import with one or two products first).
itemsNo
lot_idNoInstead of items: a catalogue lot stored by catalog_lot_build (a whole Shopify catalogue prepared for this account). Its ready items are sent 100 per call from items_from; the account defaults to the lot's target.
accountNoAccount id from list_accounts. Optional when only one account is connected.
items_urlNoInstead of items: a .json file holding the same list of items (1 to 100), for long catalogue batches: under https://vendwiser.ai/media/ (or a .json already in the seller's Shopify files at cdn.shopify.com/s/files/...).
items_fromNoWith items_url or lot_id: start at this position of the file or of the lot's ready items and send the next 100 (0, 100, 200 …).
offer_fieldsNoLeroy Merlin (Mirakl): offer fields set on every item of this call (an item's own offer_fields win), for example [{ code: "vat-lmro", value: "Standard" }, { code: "shipment-origin", value: "RO" }]. offer_fields_list shows the codes and accepted values.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / items / items / properties / offer_fields
      Added value: +{
      +  "description": "Leroy Merlin (Mirakl): the offer fields the operator defines on top of price and stock, as [{ code, value }] (or an object code -> value), for example [{ code: \"vat-lmro\", value: \"Standard\" }, { code: \"shipment-origin\", value: \"RO\" }]. offer_fields_list shows the codes and accepted values.",
      +  "items": {
      +    "properties": {
      +      "code": {
      +        "type": "string"
      +      },
      +      "value": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "code",
      +      "value"
      +    ],
      +    "type": "object"
      +  },
      +  "type": [
      +    "array",
      +    "object"
      +  ]
      +}
    • addedInput schema / properties / offer_fields
      Added value: +{
      +  "description": "Leroy Merlin (Mirakl): offer fields set on every item of this call (an item's own offer_fields win), for example [{ code: \"vat-lmro\", value: \"Standard\" }, { code: \"shipment-origin\", value: \"RO\" }]. offer_fields_list shows the codes and accepted values.",
      +  "items": {
      +    "properties": {
      +      "code": {
      +        "type": "string"
      +      },
      +      "value": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "code",
      +      "value"
      +    ],
      +    "type": "object"
      +  },
      +  "type": [
      +    "array",
      +    "object"
      +  ]
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / items / items / properties / source_sku
      Added value: +{
      +  "description": "Leroy Merlin (Mirakl): the seller's own SKU when sku is a shorter one made for this marketplace; Vendwiser remembers the pair.",
      +  "type": "string"
      +}
  3. Changed5 schema fields changed
    • addedInput schema / properties / items / items / properties / category_id / description
      Added value: +"Leroy Merlin (Mirakl): the category code as text, for example 205829|1052|R15-1001-1003 (categories_search)."
    • changedInput schema / properties / items / items / properties / category_id / type
      Previous value: -"integer"New value: +[
      +  "integer",
      +  "string"
      +]
    • changedInput schema / properties / items_from / description
      Previous value: -"With items_url: start at this position of the file and send the next 100 items (0, 100, 200 …)."New value: +"With items_url or lot_id: start at this position of the file or of the lot's ready items and send the next 100 (0, 100, 200 …)."
    • addedInput schema / properties / lot_id
      Added value: +{
      +  "description": "Instead of items: a catalogue lot stored by catalog_lot_build (a whole Shopify catalogue prepared for this account). Its ready items are sent 100 per call from items_from; the account defaults to the lot's target.",
      +  "type": "string"
      +}
    • addedInput schema / properties / skus
      Added value: +{
      +  "description": "With lot_id: send only these SKUs of the lot (for a test import with one or two products first).",
      +  "items": {
      +    "type": "string"
      +  },
      +  "maxItems": 100,
      +  "minItems": 1,
      +  "type": "array"
      +}
  4. Changed2 schema fields changed
    • addedInput schema / properties / items_from
      Added value: +{
      +  "description": "With items_url: start at this position of the file and send the next 100 items (0, 100, 200 …).",
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • changedInput schema / properties / items_url / description
      Previous value: -"Instead of items: a .json file under https://vendwiser.ai/media/ holding the same list of items (1 to 100), for long catalogue batches."New value: +"Instead of items: a .json file holding the same list of items (1 to 100), for long catalogue batches: under https://vendwiser.ai/media/ (or a .json already in the seller's Shopify files at cdn.shopify.com/s/files/...)."
  5. Changed2 schema fields changed
    • addedInput schema / properties / items_url
      Added value: +{
      +  "description": "Instead of items: a .json file under https://vendwiser.ai/media/ holding the same list of items (1 to 100), for long catalogue batches.",
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "items"
      -]New value: +[]
  6. Changed2 schema fields changed
    • addedInput schema / properties / items / items / properties / asin
      Added value: +{
      +  "description": "Amazon only: offer on this existing product page (amazon_catalog_search finds it); then only price, stock and sku are needed.",
      +  "type": "string"
      +}
    • addedInput schema / properties / items / items / properties / product_type
      Added value: +{
      +  "description": "Amazon only: the product type for a new product, for example MATTRESS (categories_search).",
      +  "type": "string"
      +}
  7. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say this is a non-read-only, non-destructive, non-idempotent write. The description adds the important behavior: it is simulated first, nothing is sent until the seller approves, and the marketplace reviews each product before it goes on sale. It also discloses marketplace-specific quirks (Temu price is the base price, category_id 0 lets Temu choose, vat_rate ignored, dimensions required) that no annotation conveys.

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?

Dense and nearly waste-free: workflow, marketplace exceptions, staging model, and alternatives each get their own short clause. The one structural weakness is ordering — the bracketed prerequisite instruction leads and the plain statement of purpose ("Propose new products") lands mid-paragraph rather than first.

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 7-parameter, multi-marketplace creation tool with an output schema and annotations, the description covers what an agent actually needs: prerequisites, staging/approval behavior, per-marketplace field requirements, variant modeling, and the batching paths. Return values are covered by the output schema, so their absence here is appropriate.

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 86%, so the schema already documents most parameters; the description still adds real meaning: Temu's weight_kg/length_cm/width_cm/height_cm requirement, category_id 0 semantics, shared product_main_id for variant items, items_from paging in 100s, and lot-level vs item-level offer_fields precedence. It does not restate the remaining parameters (account, stock, images) but doesn't need to.

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?

"Propose new products" is backed by a concrete brief: create catalog offers/items with titles, descriptions, pictures, attributes, per marketplace. The sibling set is full of offers_update_* and offers_get tools, and the description makes clear this is the creation path (variants share product_main_id, whole catalogs go through lot_id).

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 prerequisites and ordering: call listing_guide before writing any content, check the draft with listing_check because a blocking finding is refused here, and use categories_get for required attributes. It also names concrete alternatives and the conditions that select them — catalog_lot_build + lot_id for a whole Shopify catalogue, items_url for long batches, skus + items_from for a test import.

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.

Resources