mcp-server

list_ad_items

Read-onlyIdempotent

AD items — list the individual listing items of one ADS integration, the per-product rows for listing-based ad channels (e.g. Marktplaats and other classifieds, which create one ad per product). Use this to find individual ad listings and their status. Some ad channels (e.g. Google Shopping) submit the whole product set in bulk rather than as individual listings and so have no per-item rows — they return an empty list; use ad_status / get_ad_report for those. Returns {integrationId, total, returned, items:[{itemId, koongoProductId, parentId, productType, status, channelStatus, listingId, listingUrl, hasErrors, errorCount}], searchStatus}. Filter with koongo_status, channel_status, listing_id or product_id to find failures, or find a product with fulltext (SKU, name, EAN, listing id); page with limit / offset. Rows carry only identifiers + statuses (no gate); an item's actual attribute value + full error report come from get_ad_item_report. itemId is what you pass to get_ad_item / get_ad_item_report / get_ad_item_history. ad_id is the integrationId from list_ads. project_id is OPTIONAL (inferred for a single-project customer; project_id_required otherwise — then call list_projects).

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": {
      "ad_id": "<ad_id>"
    },
    "name": "list_ad_items"
  }
}

Input Schema

Name	Required	Description
`ad_id`	Yes	integrationId of the ad (from list_ads).
`limit`	No	Max items to return (page size).
`offset`	No	Number of items to skip (paging).
`fulltext`	No	Search like the integration detail table: SKU, product name, parent SKU/name, EAN/GTIN or the channel listing id (case-insensitive substring, at least 3 characters) or an exact numeric itemId.
`listing_id`	No	Filter by the item's listing id on the channel.
`product_id`	No	Filter to one Koongo product id.
`project_id`	No
`koongo_status`	No	Filter by the Koongo-side listing status.
`channel_status`	No	Filter by the channel's own listing status.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 3, 2026

addedInput schema / properties / fulltext

Added value: +{
+  "description": "Search like the integration detail table: SKU, product name, parent SKU/name, EAN/GTIN or the channel listing id (case-insensitive substring, at least 3 characters) or an exact numeric itemId.",
+  "minLength": 1,
+  "type": "string"
+}

First observedSep 1, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond the read-only and idempotent annotations, it discloses the empty-list behavior for bulk channels, the limited identifiers-and-statuses content of rows, pagination, and the exact response structure. It also clarifies that detailed attribute values and error reports require a separate call, preventing incorrect expectations about this tool's output.

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?

Nearly every sentence supplies actionable selection, invocation, or result-interpretation information. However, the long single paragraph and inline response payload make it dense to scan, and a few details duplicate the input schema.

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 nine-parameter read tool without an output schema, the description supplies the required identifier's source, optional project behavior, filtering and paging semantics, response fields, channel-specific empty results, and downstream drill-down tools. This gives an agent enough context both to select the tool correctly and to interpret and act on its results.

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 already 89%, but the description adds practical meaning by connecting filters to failure investigation, explaining fulltext use cases, and documenting project_id inference and the project_id_required recovery path. Some material repeats the schema, and the accepted values for koongo_status and channel_status remain unspecified.

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 precisely identifies the operation as listing per-product advertisement items for one ADS integration. It distinguishes listing-based channels such as Marktplaats from bulk channels such as Google Shopping and routes the latter to ad_status or get_ad_report.

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 explicitly says to use the tool to find individual listings and their statuses, and explains when it will instead return an empty list. It also provides clear follow-up guidance: get_ad_item_report for attribute values and full errors, the appropriate item-level tools for itemId, and list_projects when project selection is required.

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

All mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?