Skip to main content
Glama

Create carousel

create_carousel
Read-onlyIdempotent

Create a designed, editable social-media carousel and return a link that opens it in Slyd (the user's browser), where they can edit and export PNG/PDF/ZIP. Write the words yourself: start with a 'cover' hook, one idea per slide, end with a 'cta'. 5–10 slides is ideal. Highlight 1–3 key words per slide with asterisks. Any photo can be an https URL or a few search words. Everything visual is optional (template, format, palette, fonts, colours, textures, backgrounds, brand, freeform elements). The full option list is in get_carousel_guide.

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": {
      "slides": "<slides>"
    },
    "name": "create_carousel"
  }
}

Input Schema

NameRequiredDescriptionDefault
openNoWhat the link opens: the editor (default), a phone preview, or the export dialog.
alignNoText alignment for all layouts.
brandNoOptional. Anything omitted falls back to the user's saved brand kit in Slyd.
fontsNoFont pair: editorial (Instrument Serif + Inter), modern (Inter Tight + Inter), loud (Archivo Black + Manrope), quirky (Bricolage Grotesque + Manrope), classic (Playfair Display + Inter), warm (Fraunces + Manrope), tech (Space Grotesk + JetBrains Mono), poster (Anton + Inter), art (Syne + Space Grotesk), notes (Caveat + Manrope).
titleNoProject name in Slyd. Defaults to the hook.
accentNoShortcut for colors.accent.
colorsNoExact theme colours (e.g. brand colours). Applied on top of the palette.
formatNoSlide size. 1:1 = Square (Instagram · LinkedIn); 4:5 = Portrait (Instagram feed (best reach)); 3:4 = Tall (Instagram 2025 grid); 9:16 = Story (Stories · TikTok · Reels); 16:9 = Wide (X · Slides · YouTube). Default 4:5.
slidesYesThe slides in order. Best results: 5–10 slides, cover first, cta last.
paletteNoColour palette override: paper, noir, swiss, forest, ocean, blush, butter, lilac, clay, mono, matcha, midnight. Defaults to the template's.
textureNoTexture on every slide: none, grain, noise-heavy, paper, dots, grid, lines.
bodyFontNoExact body font, overrides `fonts`.
templateNoVisual style. editorial: Warm paper, serif headlines, quiet confidence. | noir: Near-black, electric accent, loud and modern. | swiss: Grid, red accent, uppercase poster type. | aurora: Glowing mesh gradient with crisp white type. | notebook: Dot-grid paper with handwritten energy. | photo: Full-bleed photography with a cinematic overlay. | forest: Deep green, golden accents, framed pages. | clay: Warm clay, poster type, unmissable. | blank: Theme and fonts only. Bring your own ideas.. Default: editorial.
highlightNoHow *highlighted* words look: color, italic, marker (highlighter), underline, pill.
headingFontNoExact heading font, overrides `fonts`.
textureIntensityNo0–1. Default from the template.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint, so the bar is lower; the description still adds real context by disclosing that the output is a link opened in the user's browser where they can edit and export PNG/PDF/ZIP, and that all visual options are optional with defaults. It does not cover link lifetime, persistence of the created project, or failure behavior, which is why it is not a 5.

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-loaded with purpose and return value, then authoring rules, then optionality, then the guide pointer — a sensible order with no filler. The parenthetical enumeration of visual options (template, format, palette, fonts, colours, textures, backgrounds, brand, freeform elements) largely repeats schema property names and could be trimmed.

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 16-parameter tool with deeply nested slide/element objects and no output schema, the description covers the essentials: what is produced (a link), what the agent must supply (the copy), and where the full option surface lives. Remaining gaps are link expiry and what happens to the created project in the user's account.

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 coverage is 100%, so the baseline is 3, but the description adds prioritization the schema does not: slides are the substance and everything visual is secondary, plus the asterisk highlight convention and that photos may be URLs or search phrases. It also defers the long tail of options to get_carousel_guide, which helps the agent avoid over-specifying.

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 ('Create a designed, editable social-media carousel') and names the concrete result ('return a link that opens it in Slyd'), which is exactly what an agent needs to know before calling. The 'Write the words yourself' clause makes clear the tool does not author copy, distinguishing its role from the guide tool it points at.

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?

Gives clear positive guidance: cover hook first, one idea per slide, cta last, 5–10 slides ideal, 1–3 highlighted words per slide, and routes to get_carousel_guide for the full option list. It never states when not to use it or how it relates to read_carousel_link, so a routing alternative is left implicit.

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