OrgLines

Creatives: order creatives

creative_order

Order ad creatives: brief, goal / channel, formats, styles (or "random12"), brand kit, texts (or "auto"), language, references, variants (1–8), quality (draft / final). SPENDS AI credits, charged up front at confirmation; renders that fail are refunded. Call creative_estimate first and tell the person the price. Pass an idempotency_key (any unique string per intended order). Returns order_id at once; rendering takes about 1–3 minutes. DO NOT order again if the wait was cut off — poll creative_get(order_id) instead (не замовляй повторно, опитуй creative_get). CONFIRMATION: this tool is PROPOSED, never performed directly. You get status='confirmation_required' with an action_id and a plan_token, and the write happens only after confirm_action.

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": {
      "brief": "<brief>"
    },
    "name": "creative_order"
  }
}

Input Schema

Name	Required	Description
`goal`	No
`task`	No	Optional hint for the model router.
`brief`	Yes	What to advertise: product / service, offer, for whom.
`event`	No	Facts of a course / webinar / seminar / conference, printed EXACTLY as given (never invented): the event_poster layout sets them as the picture, other layouts get "date · time · place" in the offer line.
`texts`	No	"auto" (default) = AI writes headline / CTA / caption (+20 credits once); or the exact texts to put on the banner (no copy charge).
`preset`	No	A ready niche task (courses, consulting, trainings & events — see creative_options.presets): fills goal, channel, formats, layouts, styles and variants you leave out, adds the niche copy rules and a real-photo direction (unretouched expert, real hall). Some need facts: webinar / cohort_enrolment → event.date; seminar_invite → event.date + event.place; early_bird → event.date + event.early_price; client_case → big_number.
`styles`	No	Style slugs from creative_style_list (cycled over variants), or "random12" for different random styles.
`channel`	No	e.g. instagram_post, facebook, linkedin, tiktok, pinterest, google.
`formats`	No	Formats (≤4) — keys or aspect ratios from creative_options. Default ["square"].
`layouts`	No	Banner layout per variant (cycled). "auto" (default) picks a DIFFERENT layout for each variant to fit its style and the task: full_bleed (photo edge to edge, headline on its calm zone, no panel), editorial_split (magazine page, serif), color_block (flat bold colour + round photo), swiss_grid (grid, facts in columns), minimal_object (one object, a lot of air), big_typography (words only, no image), collage (the subject cut out of the photo over huge capitals + a round offer sticker), big_number (ONE real number from the brief as the picture, no image; needs big_number or a number in the brief), event_poster (the event's date huge + time, place, speaker, price, seats; no image; needs event.date or event.place). Layouts without an image cost 5 credits per creative at any quality. See creative_options.layouts.
`quality`	No	draft = 5 credits per image (default), final = 20.
`audience`	No
`language`	No	uk (default), en, de, …
`variants`	No	Default 4.
`big_number`	No	The number for the big_number layout exactly as the client states it, with its unit: "24", "−30%", "1 200 ₴", "15+". Never invent one. Without it the copy model takes a number written in the brief; with no number at all the auto-pick never chooses big_number.
`references`	No	reference_id values from creative_reference_upload.
`brand_kit_id`	No	A brand kit of THIS cabinet (brand_kit_list).
`idempotency_key`	No	Same key = the same order, never a second charge.
`big_number_label`	No	≤ 4 words printed above the number ("годин доставки").
`big_number_source`	No	Optional source footnote under the number ("за даними CRM, 2025").

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.2/5.0

Behavior3/5

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

The description adds substantial behavior beyond the annotations: credits are charged up front, failed renders are refunded, rendering is asynchronous (~1-3 min) with an immediate order_id, and an idempotency_key prevents double charges. However, it states the tool is "PROPOSED, never performed directly" and returns status='confirmation_required', which conflicts with readOnlyHint=false and destructiveHint=false — the failure to disclose that this is a two-step confirmed write is a significant gap, though the confirmation mechanics are partly described.

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?

Mostly front-loaded and dense with high-value warnings set off in caps (SPENDS AI credits, DO NOT order again, CONFIRMATION). The parenthetical Ukrainian repetition ("не замовляй повторно, опитуй creative_get") and some redundancy around the confirmation flow cost it a point, but nothing is wasted overall.

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 20-parameter tool with a nested event object and no output schema, the definition covers cost, refunds, timing, idempotency, and the confirmation handshake — everything an agent needs to call it safely. It explicitly resolves the most likely failure mode (re-ordering after a timeout).

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?

Schema description coverage is 90% and nearly every parameter has a rich description, so the baseline is 3. The description reinforces a few key semantics (variants 1-8, quality draft/final, styles "random12", texts "auto") but adds no format or constraint information the schema does not already contain.

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+resource ("Order ad creatives") and immediately enumerates the dimensions of the order (brief, goal/channel, formats, styles, brand kit, texts, language, references, variants, quality). It is clearly distinguishable from creative_estimate, creative_get and creative_refine, which are named in the text.

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 routing rules: call creative_estimate first and quote the price, do not re-order after a cut-off wait but poll creative_get(order_id), and go through confirm_action for the actual write. It also names the when-not condition (never performed directly) and the prerequisite for the charged copy step.

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

All OrgLines 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?