mcp-server

run_ai_source_import

Destructive

Apply stored additional-source (AI) values onto products (they land as custom_). Use this to apply them after the last set_ai_source batch, after delete_ai_source, or to retry a failed import. Overwrites the products' existing custom_ values. Also downloads the additional-source URLs already configured on this project; takes no URL. Returns {status:'dispatched'|'skipped', type}; 'skipped' = store data not connected. ASYNC: poll get_import_status until the newest additional_source run has running:false and status 'ok'. 'addon_required' (HTTP 403) = not included in this Koongo account; do not retry. project_id OPTIONAL.

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": "run_ai_source_import"
  }
}

Input Schema

Name	Required	Description	Default
`project_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 3, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description goes further by specifying what is destroyed (existing custom_<code> values are overwritten). It also discloses the async dispatch model, the {status, type} return shape, the meaning of 'skipped', and the addon_required error semantics — all beyond structured fields.

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 action and effect, then usage, return shape, async protocol, and error handling in a logical order. The telegraphic, clause-heavy style is efficient but slightly dense, with several distinct facts packed into single sentences.

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?

No output schema exists, and the description supplies the return shape, the async polling protocol, the skipped-state meaning, and the non-retryable error case. For a destructive async import with one optional parameter, nothing material is missing for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single parameter has 0% schema description coverage, so the description must compensate. It notes that project_id is OPTIONAL and that no URL is taken, but never explains what project_id scopes or what the default is when omitted. Partial compensation only.

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 ('Apply stored additional-source (AI) values onto products') and even names the resulting field shape (custom_<code>). The parenthetical '(AI)' plus 'additional-source' clearly separates it from the sibling run_api_source_import, and the 'takes no URL' note removes the main ambiguity between the two.

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 triggers: after the last set_ai_source batch, after delete_ai_source, or to retry a failed import. It also names the follow-up tool (get_import_status) with the exact condition to poll for, and states a clear when-not: on 'addon_required' (403), do not retry.

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?