Skip to main content
Glama
@cmssy/mcp-server

@cmssy/mcp-server

Official

Get product bulk job

get_product_bulk_job
Read-only

Check a bulk product job's status and progress by jobId, or find the queued or running job for a model by modelId. Returns processed counts, changes, skips, and failure reasons.

Instructions

Read a background product bulk job's status and progress, by jobId or - for the job still queued or running on a model - by modelId (jobId wins when both are given). status goes queued -> running -> completed or failed; processed of total is the progress, deleted/updated what changed, skippedCount and skipped (first 20, with reason) what a delete left in place. A failed job carries failureReason (stalled, modelUnavailable, invalidPatch, enqueueFailed, unexpected). job is null when the id is unknown or the model has no active job. Jobs run in batches of a few hundred products: check again later rather than in a tight loop.

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": "get_product_bulk_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobIdNoThe job id a start_bulk_*_products tool returned. When given, modelId is ignored.
modelIdNoThe product model's id or slug: returns the job still queued or running for it, if any

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.146.2

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare a safe read, and the description still adds substantial behavior: the queued -> running -> completed/failed lifecycle, the meaning of processed/total/deleted/updated/skipped, the enumerated failureReason values (stalled, modelUnavailable, invalidPatch, enqueueFailed, unexpected), and the null-tool for unknown ids. That is exactly the kind of state and failure disclosure an agent needs to interpret results.

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 the core action and key precedence rule, then progressively more detailed field semantics and finally the polling advice. It is dense but every clause carries information; the only cost is that the return-field inventory reads as a run-on paragraph rather than scannable structure.

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?

There is no output schema, so the description carries the full burden of explaining return values, and it does: status values, progress fields, skip details, failure reasons, and the null case. Combined with the polling-cadence note, an agent has everything needed to call and interpret this tool correctly.

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, and the description earns more by explaining consequences rather than restating types: modelId only returns the job that is still queued or running, and 'job' is null when the id is unknown or the model has no active job. This makes the semantics of an empty result unambiguous.

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 ('Read a background product bulk job's status and progress') and pins the two lookup keys: jobId or modelId. It is clearly a status-read companion to the start_bulk_*_products tools rather than a mutation, so an agent can place it against its siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete selection rules: use jobId when you have the id a start_bulk_*_products call returned, use modelId to find the job still queued or running for a model, and jobId wins when both are supplied. It also tells the agent to check again later in batches rather than in a tight loop. It stops short of stating when not to call it at all (e.g. once a job is completed and the result consumed), so this is a strong 4 rather than a 5.

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