Skip to main content
Glama

oriiion

Create Carousel (from a brief, a product or an article)

create_carousel

Write and design a CAROUSEL from scratch — 4-10 branded slides — when there are no images and no PDF, only a subject. This is the tool for "make a carousel about X", "a LinkedIn document carousel about X", "a slide deck on X". It writes one idea per slide from the brief and the account's own business profile, designs them in the brand, and produces ONE draft post: the slides publish to Instagram, and LinkedIn gets the same deck as a swipeable PDF document rather than an image gallery. Use create_carousel_from_images instead when the user supplies the pictures, and redesign_document when they supply a PDF. Runs in the background for a few minutes — poll get_task_status with the returned taskId, and give the user the returned ownerLink so they can see the slides. A productId whose product has at least two photos always becomes a carousel of those photos, and an account with AI images turned off gets its OWN photos for any source — no slides are designed and no text is drawn on them (the caption carries the message, the brand overlay adds the account's text design); with AI images off it is refused when the account has fewer than two photos. An account that has uploaded its own carousel design (Settings → Brand → Carousels) gets every designed deck in it, and a news-article deck is always designed in it, even with AI images off. For a product, pass design 'template' to design the slides in that uploaded design with the product's photos laid in, instead of a carousel of the photos; it is refused when the account has no uploaded design.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topicNoWhat the carousel should say, in the user's own words. Required unless productId or articleId is given, where it becomes the extra steer.
designNoWith productIds: 'photos' for the products' own photos instead of a designed deck. With productId: 'photos' (default): a carousel of the product's own photos. 'template': slides designed in the account's own uploaded carousel design with the product's photos laid in — only when the account has uploaded one.
articleIdNoMake the deck a commentary on one news article (from list_news).
productIdNoMake the carousel about one product — 'shopify-42' or 'feed-17' (from list_products). A product with two or more photos becomes a carousel of those photos with no text on them; its description writes the caption.
productIdsNoSeveral products (list_products ids), with topic as the angle. Default: a DESIGNED deck — their catalogue facts fill the slides and their photos are composed into the design. With design 'photos': a carousel of their own photos instead, a slide per product, no text drawn on them. Not together with productId or articleId.
slideCountNoHow many slides, 4-10. Default 8.
scheduledForNoISO datetime to schedule the finished post for. Omit to leave it as a draft.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

With annotations only covering the safety profile (readOnlyHint=false, non-idempotent, non-destructive), the description carries the real behavioral load: background execution taking minutes, polling via get_task_status with the returned taskId, returning an ownerLink, and the downstream publish semantics (IG slide post, LinkedIn PDF document). It could still say more about duplicate drafts on repeat calls, but the disclosure is well beyond what the annotations provide.

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-loads the core purpose and alternative routing, and nearly every sentence carries decision-relevant information. It is dense and the middle clauses chain several conditional rules together in one long sentence, which hurts scanability, but there is little pure filler.

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?

With 7 parameters, no output schema, and a genuinely complex tool, the description still covers initiation (background task), tracking (taskId + get_task_status), user-facing artifact (ownerLink), downstream destinations, and the source-dependent branching. Nothing an agent needs to call this correctly appears to be missing.

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?

Schema description coverage is 100%, so baseline is 3, but the description adds cross-parameter behavior the schema cannot express: productId vs productIds interactions, the 'photos' vs 'template' design rule, the two-photo threshold, and the default designed deck for productIds. That is meaningful semantic value beyond the field-level docs.

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+scope: 'Write and design a CAROUSEL from scratch — 4-10 branded slides', and explicitly names the conditions that separate it from siblings ('when there are no images and no PDF, only a subject'). It also names two siblings it is NOT for (create_carousel_from_images, redesign_document), so an agent can disambiguate without opening schemas.

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 when-to-use triggers ('make a carousel about X', 'a LinkedIn document carousel about X'), names the alternatives and the conditions that select them, and even states refusal conditions (AI images off with fewer than two photos; 'template' with no uploaded design). This is about as complete as routing guidance gets.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources