Creadal

Generate a presentation

generate_presentation

Generate a complete, editable presentation or document from a prompt (for a social post, story or ad use create_social_design instead: it starts from a designed template and places the member's own picture and logo). Waits for the result when generation is quick; otherwise returns a job to poll with get_job. The composed deck contains laid-out text, a theme, and speaker notes; per-slide images are generated in the creadal editor. Requires the 'generate' scope.

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": {
      "prompt": "<prompt>"
    },
    "name": "generate_presentation"
  }
}

Input Schema

Name	Required	Description
`motion`	No	Entrance motion on the slides; defaults to subtle.
`prompt`	Yes	The brief, e.g. 'a 6-slide pitch deck for an eco water bottle'.
`sources`	No	Grounding material the outline is based on.
`themeId`	No	A built-in theme id from list_themes (e.g. 'theme-slate'); omit for an auto-picked look.
`language`	No	Write all text in this language, e.g. 'Spanish'.
`pageCount`	No
`designType`	No	Defaults to deck.
`templateId`	No	A template id from list_templates: the deck is composed on that template's layout system and theme.
`brandPalette`	No	Brand hex colors to ground the theme in.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 17, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Beyond the annotations (openWorld, non-idempotent, mutating-but-non-destructive), the description discloses the required 'generate' scope, the wait-or-poll execution model, and the shape of the produced deck (laid-out text, theme, speaker notes, per-slide images generated in the editor). That is meaningful added context. It stops short of noting cost/quota consumption or failure behavior, which a generative tool would ideally surface.

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 the core action, then the sibling disambiguation, then execution model, then output composition and scope. Dense but every sentence carries information. Slightly long and the parenthetical is heavy, but nothing is redundant.

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 9-parameter generative tool with no output schema, the description covers the async return path, the required scope, and the composition of the result, which is what an agent needs to invoke it correctly. It omits cost/quota implications and error behavior, minor but real gaps for a billed generation endpoint.

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 89%, so parameters like motion, themeId, templateId, sources, and brandPalette are already documented in the schema. The description adds only marginal meaning, mainly clarifying that output can be a 'document' (mapping to designType) and that generation is prompt-driven. Baseline 3 is appropriate when the schema carries the parameter burden.

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 ('Generate a complete, editable presentation or document from a prompt') and immediately distinguishes itself from the sibling create_social_design by name and mechanism (designed template + member's picture/logo). An agent can route between the two generators without opening either schema.

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 an explicit alternative with the selecting condition ('for a social post, story or ad use create_social_design instead'). It also explains the synchronous-vs-async branch, telling the agent to poll get_job when generation is slow, which is exactly the when-to-do-what guidance an agent needs.

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

All Creadal 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?