Seliee

Create Articles Order

create_articles_order

Destructive

Create an AI article order: one article is written for each topic, priced per topic. seliee_articles_order_language takes a CONTENT_LANGUAGES value (turkish, english, german, ...), never a locale code. ai_account_id / ai_account_uuid name the account of seliee_articles_order_ai_provider (optional for llama, answered by Seliee AI); the order and each of its queued topics keep both the id and the uuid. seliee_articles_order_options is the linking / targeting / publish block (seliee_articles_order_has_article_links, _has_websites_select + _websites_uuids (full keys: seliee_articles_order_websites_uuids), _has_collections_select + _collections_uuids (seliee_articles_order_collections_uuids), _has_collections_random, _collection_texts, _has_cnames + _cnames_piece, _has_publish + _publish_datetime, _has_publish_range + _publish_start_datetime / _publish_end_datetime, seliee_articles_order_article_title (the title of the order's article, no AI title), seliee_articles_order_website_uuid (the website the article is written on), seliee_articles_order_brief (writing instructions, at most 4000 characters, replacing the writer prompt), and seliee_articles_order_redirect = {url, utm, cta_text (string or list of anchors, one picked per article), cta_position (start|middle|end|random, default end)}: each article gets a published /r/ redirect on its website to url (utm values may use {language} and {article_slug}); cta_text also puts that link into the article); defaults to no linking.

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_articles_order_title": "<seliee_articles_order_title>",
      "seliee_articles_order_topics": "<seliee_articles_order_topics>",
      "seliee_articles_order_language": "<seliee_articles_order_language>"
    },
    "name": "create_articles_order"
  }
}

Input Schema

Name	Required	Default
`customer_id`	No
`ai_account_id`	No
`customer_uuid`	No
`ai_account_uuid`	No
`seliee_articles_order_note`	No
`seliee_articles_order_model`	No
`seliee_articles_order_title`	Yes
`seliee_articles_order_topics`	Yes
`seliee_articles_order_options`	No
`seliee_articles_order_language`	Yes
`seliee_articles_order_ai_provider`	No	openai

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 3, 2026

addedInput schema / properties / ai_account_uuid

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

AddedNov 3, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already say readOnly=false, destructive=true, idempotent=false, so the safety profile is covered. The description goes further with real behavioral consequences: each article gets a published /r/<random> redirect on its website, utm values support {language} and {article_slug} placeholders, the brief replaces the writer prompt and caps at 4000 characters, and linking defaults to off. It stops short of stating the order's lifecycle (queued, async, cost implications).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose sentence is well front-loaded, but the remainder collapses into a single dense paragraph stuffed with fully prefixed key names and nested parentheticals, which is hard for an agent to parse quickly. The information is largely useful, but the structure could be broken into a short options list.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a complex, non-idempotent creation tool with no output schema, so the description should say what comes back (order id/uuid, queued topic status) and how errors or partial failures are surfaced; it only gestures at this with 'the order and each of its queued topics keep both the id and the uuid'. The options block is well covered, but the return and failure behavior remain thin.

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 11 parameters and an untyped 'additionalProperties: true' options object, the description carries nearly all the semantic load: it names the actual options keys, explains the full vs short key forms, gives the language enum examples, defines cta_position values and its default, and describes redirect behavior. A few top-level parameters (customer_id/customer_uuid, note, model, title, topics) are still unexplained.

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?

Opens with a specific verb plus resource and even states the unit economics: 'Create an AI article order: one article is written for each topic, priced per topic.' That is enough for an agent to separate it from create_article, create_auto_article and create_collections_order without opening any schema.

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

Usage Guidelines3/5

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

The description implies usage through the per-topic pricing model and the note that ai_account_id is optional for llama, but it never states when to choose this tool over create_auto_article or create_article, nor any prerequisites or when-not-to-use conditions.

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

All Seliee 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?