Skip to main content
Glama
@cmssy/mcp-server

@cmssy/mcp-server

Official

Start bulk delete products

start_bulk_delete_products
Destructive

Starts a background job to permanently delete products matching a filter when more than 1000 match, then track batch progress with get_product_bulk_job.

Instructions

Start a background job that permanently deletes every product matching the filter. Use it instead of bulk_delete_products when more than 1000 products match. Returns the job at once; it runs in batches, so follow its progress with get_product_bulk_job. A model runs one job at a time: if one is already queued or running the start is refused - read it with get_product_bulk_job by modelId. As with bulk_delete_products, a product still referenced by an open order or a page block is skipped; the finished job reports skippedCount and the first skipped products with their reason.

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": {
      "modelId": "<modelId>"
    },
    "name": "start_bulk_delete_products"
  }
}

Input Schema

NameRequiredDescriptionDefault
filterNoProducts to delete; omit to delete every product of the model
modelIdYesThe product model's id or slug (from list_models)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.146.2

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true, but the description adds substantial context beyond them: the operation is asynchronous and returns the job immediately, it runs in batches, one job per model at a time with refusal semantics, and products referenced by open orders or page blocks are skipped rather than failing the job, with skippedCount reported on completion. That is exactly the behavior an agent needs before triggering an irreversible operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five tight sentences, front-loaded with the action and followed by routing, async behavior, concurrency, and skip semantics in priority order. No sentence is decorative and nothing is repeated from the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter destructive tool with no output schema, the description covers return behavior, follow-up tooling, concurrency limits, and partial-success reporting. It stops short of naming the finished job's other fields or how long jobs are retained, which are minor given get_product_bulk_job presumably handles them.

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, but the description adds meaning beyond the schema by framing filter as a match condition on the delete set and tying modelId to job retrieval ('read it with get_product_bulk_job by modelId'). It does not restate the filter sub-fields, which the schema already documents.

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 opens with a specific verb and resource ('Start a background job that permanently deletes every product matching the filter') and immediately distinguishes it from the sibling bulk_delete_products by match count. An agent can tell which of the two delete tools to pick without opening either 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 an explicit selection rule versus bulk_delete_products ('more than 1000 products match'), names get_product_bulk_job for progress tracking, and states the one-job-per-model constraint plus the recovery path when a start is refused. Both when-to-use and what-to-do-on-failure are covered.

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

Deploy Server

Other Tools