SelieeAI

Create Collections Order

create_collections_order

Destructive

Create an AI collection order: the worker_orders_collections_auto_create worker writes one collection per topic (a collection name or subject, e.g. "Dentists in Berlin"), one a minute, priced per topic. Each collection is created on one of seliee_collections_order_websites_uuids (the merchant's own websites), with the topic as title, AI keywords and description, and, by default, AI written HTML content and FAQs (has_content, has_faqs). It stays an unpublished draft unless has_publish is true. A topic whose slug already exists on the picked website finishes with that collection instead of a duplicate. seliee_collections_order_language takes a CONTENT_LANGUAGES value (turkish, english, ...), never a locale code. ai_account_id / ai_account_uuid name the account of the provider (optional for llama, answered by Seliee AI). Poll get_collections_order for the state of each topic.

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": {
      "seliee_collections_order_title": "<seliee_collections_order_title>",
      "seliee_collections_order_topics": "<seliee_collections_order_topics>",
      "seliee_collections_order_language": "<seliee_collections_order_language>",
      "seliee_collections_order_websites_uuids": "<seliee_collections_order_websites_uuids>"
    },
    "name": "create_collections_order"
  }
}

Input Schema

Name	Required	Default
`has_faqs`	No
`customer_id`	No
`has_content`	No
`has_publish`	No
`ai_account_id`	No
`customer_uuid`	No
`ai_account_uuid`	No
`seliee_collections_order_note`	No
`seliee_collections_order_model`	No
`seliee_collections_order_title`	Yes
`seliee_collections_order_topics`	Yes
`seliee_collections_order_language`	Yes
`seliee_collections_order_ai_provider`	No	openai
`seliee_collections_order_websites_uuids`	Yes

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?

Beyond the annotations, the description discloses meaningful behavior: one collection per topic per minute, per-topic pricing, default AI-generated content and FAQs, draft versus published state, and slug-collision reuse instead of duplication. These are operational traits an agent could not infer from the schema or annotations alone.

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?

The description is dense but front-loaded and every sentence adds operational detail: purpose, worker behavior, destination, defaults, publication behavior, language constraint, provider account, and polling. There is no filler or repeated schema information.

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 14-parameter mutation tool with no output schema, the description covers the core creation workflow and tells the agent how to monitor results via get_collections_order. It is not fully complete because several optional parameters and their effects remain unexplained, but the critical behavior is present.

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?

With 0% schema description coverage across 14 parameters, the description carries the burden well for the important fields: topics, websites_uuids, language, has_content, has_faqs, has_publish, and ai_account_id/ai_account_uuid. It omits meaning for title, note, model, ai_provider, and customer fields, which keeps it from a 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?

The description opens with a specific verb and resource: 'Create an AI collection order,' then immediately defines that the worker writes one collection per topic. This clearly distinguishes it from the singular sibling create_collection and the separate create_articles_order.

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?

It gives clear context for using this tool to create a batch order of AI-generated collections, and it explicitly directs the agent to poll get_collections_order for per-topic state. It does not explicitly compare against alternatives such as create_collection or create_articles_order, so it stops short of full when/when-not guidance.

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

All SelieeAI 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.