Skip to main content
Glama
Sign In

Renderball

by com.renderball
OverviewDiscussionsAdmin

Create a deck

create_deck

Start a new presentation from a brief, the brand and your outline. The brand: if you can open the brand's website, read its real colours and fonts there first and declare them — the lead colour is usually the main buttons and the large coloured areas, not the link colour — and always give the website; never invent a colour. With the outline the reply carries PAGE 1'S BRIEF; write page 1 and send it with submit_page — each reply carries the next page's brief.

Input Schema

NameRequiredDescriptionDefault
sizeNoThe page size, any you need: "wide" 1920×1080 (slides, the default), "square" 1080×1080 (a post), "vertical" 1080×1920 (a story, a poster, a menu), or any width × height in px written "1200x628" (each side 100 to 4096): a link card 1200x628, a portrait post 1080x1350, an A4-shaped page 1240x1754, a banner 1500x500. Pick the size the person asked for: never draw a page turned sideways to fake another size.
brandNoThe brand as YOU know it: name, and only the colours, fonts and logo you actually have. Never guess a colour; leave it out.
briefYesWhat the deck is for, who it is for, what it should argue and ask. Real facts only; the truth check refuses invented figures.
pagesNoHow many pages you intend to write (default 5). Ignored when `outline` is given.
outlineNoYour page-by-page outline (one entry per page: label, description, visual_concept, content with a headline). Send it here and the reply carries the brief to write from (page 1's brief when the deck is written page by page) — one call instead of create_deck + write_outline.
brand_urlNoKey holders only: a website Renderball reads for colours, fonts and logo when no brand is declared.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / size / description
      Previous value: -"The page size: wide 1920×1080 (slides, the default), square 1080×1080 (a post), vertical 1080×1920 (a story, a poster, a menu). Pick the size the person asked for: never draw a page turned sideways to fake another size."New value: +"The page size, any you need: \"wide\" 1920×1080 (slides, the default), \"square\" 1080×1080 (a post), \"vertical\" 1080×1920 (a story, a poster, a menu), or any width × height in px written \"1200x628\" (each side 100 to 4096): a link card 1200x628, a portrait post 1080x1350, an A4-shaped page 1240x1754, a banner 1500x500. Pick the size the person asked for: never draw a page turned sideways to fake another size."
    • removedInput schema / properties / size / enum
      Removed value: -[
-  "wide",
-  "square",
-  "vertical"
-]
    • addedInput schema / properties / size / maxLength
      Added value: +24
  2. Changed1 schema field changed
    • addedInput schema / properties / size
      Added value: +{
+  "description": "The page size: wide 1920×1080 (slides, the default), square 1080×1080 (a post), vertical 1080×1920 (a story, a poster, a menu). Pick the size the person asked for: never draw a page turned sideways to fake another size.",
+  "enum": [
+    "wide",
+    "square",
+    "vertical"
+  ],
+  "type": "string"
+}
  3. Changed2 schema fields changed
    • changedInput schema / properties / brand / properties / accent / description
      Previous value: -"The lead brand colour: read it from their website if you can open it (usually the main buttons and the large coloured areas, not the links) or from the user's material. Never invent one."New value: +"The lead brand colour (usually the main buttons and the large coloured areas, not the links), only if you know it from the user, their material or their site. Never invent one."
    • changedInput schema / properties / outline / description
      Previous value: -"Your page-by-page outline (one entry per page: label, description, visual_concept, content with a headline). Send it here and the reply carries the WRITING BRIEF — one call instead of create_deck + write_outline."New value: +"Your page-by-page outline (one entry per page: label, description, visual_concept, content with a headline). Send it here and the reply carries the brief to write from (page 1's brief when the deck is written page by page) — one call instead of create_deck + write_outline."
  4. Changed1 schema field changed
    • changedInput schema / properties / brand / properties / accent / description
      Previous value: -"The lead brand colour. ONLY if you know it (from their site's stylesheet or the user's material); never guess."New value: +"The lead brand colour: read it from their website if you can open it (usually the main buttons and the large coloured areas, not the links) or from the user's material. Never invent one."
  5. Changed1 schema field changed
    • changedInput schema / properties / brand / properties / website / description
      Previous value: -"Their website, e.g. yourcompany.com — used for the wordmark's source, not read."New value: +"Their website, e.g. yourcompany.com. With an account, when you declare no colours, Renderball reads the site for its colours, fonts and logo — so give the website and leave colours you do not know out."
  6. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations only declare write/non-destructive/open-world. The description adds substantive behavior beyond that: the call returns page 1's brief, the flow is iterative with each reply carrying the next page's brief, and brand colours must be sourced from the real site rather than guessed. Auth/rate details are absent but the workflow contract is well disclosed.

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?

Purpose is front-loaded, followed by brand guidance and then the post-creation workflow. It is dense but each sentence carries actionable instruction; the brand-colour digression is the only slightly padded element.

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 6-parameter, nested-object, no-output-schema tool, the description covers what the call produces (the next page's brief) and how to continue with submit_page, which is the critical missing piece from structured fields. Return-shape detail and the outline-vs-pages distinction remain unstated.

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 100%, so the schema already carries parameter meaning. The description restates the brand-colour rule (lead colour = buttons/large areas, not link colour) and the website requirement, which largely duplicates the accent and website schema descriptions rather than adding new semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence gives a specific verb and resource ('Start a new presentation') and names its three inputs (brief, brand, outline). It does not explicitly differentiate itself from siblings like write_outline or submit_deck, though the mention of submit_page hints at the workflow.

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?

It gives clear operational context: read the brand's site for real colours first, always supply the website, never invent a colour, and after creation the reply carries page 1's brief which you write and send via submit_page. It stops short of stating when to choose create_deck over alternatives such as write_outline or the outline-vs-pages trade-off.

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

All Renderball toolsInspect
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