Skip to main content
Glama

Import: Delete Products

delete_pre_publish_products
Destructive

[Import List Product] [What it does] Permanently deletes 1-20 exact Import List products by import_item_id; it never selects products by keyword or filter. [When to use] Call after the user reviews and selects exact products with list_pre_publish_products to remove; trigger words: delete import list product, clean up import list, remove pre-publish products. [When not to use] To find or narrow removal candidates, use list_pre_publish_products first. This tool does not remove products already published to a store. [How to use] Pass 1-20 exact import_item_ids copied from list_pre_publish_products. A successful response returns only the normalized import_item_ids submitted after Product BFF accepts the delete call; it does not provide per-item outcomes. If the outcome is unclear, re-check with list_pre_publish_products instead of retrying the delete. [Side effects] Permanently removes products from the Import List; irreversible. Dispatch once. [Confirmation] Requires user confirmation, skippable per policy; show the exact products before calling. [Follow-up] If the outcome is unclear, verify which products remain with list_pre_publish_products.

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": {
      "import_item_ids": "<import_item_ids>"
    },
    "name": "delete_pre_publish_products"
  }
}

Input Schema

NameRequiredDescriptionDefault
import_item_idsYesComplete set of one to 20 exact import-list item IDs approved in the user's latest explicit confirmation. Copy every ID from the latest list_pre_publish_products result and submit the set in one call. Use an array containing one ID for a single product. Paste JSON example: ["2085934367682592768"].

Output Schema

NameRequiredDescriptionDefault
import_item_idsYesNormalized import-list item IDs submitted to the acknowledged delete workflow
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 destructiveHint=true and idempotentHint=false, but the description adds real value on top: irreversibility, dispatch-once guidance, the confirmation requirement, and the unusual return contract (only normalized IDs echoed, no per-item outcomes). The only deduction is that the response semantics are partially duplicated in the output schema's territory rather than fully elaborated, but the 'do not retry, re-check with list' instruction is exactly the kind of behavioral context annotations cannot carry.

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 make it skimmable and the destructive scope is front-loaded, which matters for a delete tool. There is some redundancy: the 're-check with `list_pre_publish_products` instead of retrying' idea appears in both [How to use] and [Follow-up], and could be stated once.

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 destructive, single-parameter batch delete, it covers prerequisites (prior listing and user confirmation), irreversibility, the no-retry rule, and where to verify afterwards. Output schema exists, yet the description still correctly flags that the response has no per-item outcome — the one non-obvious gap an agent would otherwise trip on.

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 description coverage is 100%, so the baseline is 3; the description earns a bump by emphasizing the provenance of the IDs (copied from the latest `list_pre_publish_products` result, submitted as one batch, array of one for a single item), which is selection semantics rather than restated type info. The 1-20 bound itself is already in the schema and is repeated here, so it is not a full 5.

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?

Opens with a specific verb and resource ('Permanently deletes 1-20 exact Import List products by `import_item_id`') and explicitly negates the adjacent behavior an agent might assume ('never selects products by keyword or filter'). This separates it cleanly from `list_pre_publish_products` and the other pre-publish siblings.

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?

Gives explicit when-to-use triggers ('delete import list product, clean up import list'), an explicit when-not-to-use with the named alternative `list_pre_publish_products`, and a scope exclusion ('does not remove products already published to a store'). An agent has no inference left to do about routing.

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.