SelieeAI

Create Auto Collection

create_auto_collection

Destructive

"Create Auto Collection": queue one AI-written collection about subject (a collection name or subject, e.g. "Dentists in Berlin") on the website seliee_website_uuid. A one-topic collection order the worker_orders_collections_auto_create worker writes within a few minutes (title, keywords, description, content and FAQs); it stays an unpublished draft unless has_publish. Returns the order id / uuid: poll get_collections_order for its state. Language takes a CONTENT_LANGUAGES value; model picks the writing model (list_ai_accounts shows the account and its models). title: when given it is the collection's title (else the subject is). publish_datetime: the publish date (YYYY-MM-DD). The content is 800 characters at most.

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": {
      "subject": "<subject>",
      "seliee_collections_order_language": "<seliee_collections_order_language>",
      "seliee_website_uuid": "<seliee_website_uuid>"
    },
    "name": "create_auto_collection"
  }
}

Input Schema

Name	Required	Default
`model`	No
`title`	No
`subject`	Yes
`customer_id`	No
`has_publish`	No
`ai_account_id`	No
`customer_uuid`	No
`ai_account_uuid`	No
`publish_datetime`	No
`seliee_website_uuid`	Yes
`seliee_collections_order_language`	Yes
`seliee_collections_order_ai_provider`	No	openai

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 3, 2026

addedInput schema / properties / publish_datetime

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Publish Datetime"
+}

addedInput schema / properties / title

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Title"
+}

AddedNov 3, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already flag a non-idempotent, destructive write; the description adds genuinely new behavior: asynchronous worker that completes in a few minutes, result stays an unpublished draft unless `has_publish`, returns an order id/uuid for polling, and content is capped at 800 characters. It does not explain why destructiveHint is true for what reads as a draft-producing create, but nothing contradicts the annotations.

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?

Front-loaded with a quoted name plus the one-line purpose, then grouped details (async behavior, return/polling, then per-parameter notes). Dense but every sentence carries information; no filler.

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 12-parameter async mutation with no output schema, the description covers what an agent needs to call it and what to do next (poll get_collections_order for state). Residual gaps are the identity/provider parameters and whether customer/ai-account ids are required in practice.

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 the description compensates for the key fields: `title` overrides the subject as the collection title, `publish_datetime` is YYYY-MM-DD, the language field takes a CONTENT_LANGUAGES value, and `model` is resolved via `list_ai_accounts`. Five optional parameters (customer_id/customer_uuid, ai_account_id/ai_account_uuid, seliee_collections_order_ai_provider) remain unexplained, which is why this is not 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?

States a specific verb and resource (queue one AI-written collection order about `subject` on `seliee_website_uuid`) and implicitly separates itself from the manual `create_collection`/`create_collections_order` siblings by naming the `worker_orders_collections_auto_create` worker and the auto-generated outputs (title, keywords, description, content, FAQs).

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?

Clear context for when to call: you want a fully AI-written one-topic collection rather than a manually authored one, and a follow-up path is specified ('poll get_collections_order'). It does not explicitly exclude the sibling create_collection/create_collections_order, so selection between 'create now' tools still requires inference.

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.