Skip to main content
Glama

Generate a thumbnail

generate_thumbnail

Create a Roblox thumbnail from a text prompt and reference image; includes style-guide enhancement and optional direct publishing to Roblox.

Instructions

Make a new thumbnail image with the site's AI pipeline — the same one the generator page uses — from a prompt and at least one reference image. The prompt is rewritten against the studio style guide first unless enhance is turned off. The result is written to a file on this machine so it can be looked at, and saved to the project's history. Pass publish to send it straight to Roblox, which is only worth doing when the image has already been agreed on; otherwise generate, look at it, then call upload_thumbnail.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
gameYesGame name or universe id. The generation is saved to this project.
modelNoWhich image model to use. Defaults to gemini.
promptYesWhat the thumbnail should show.
enhanceNoRewrite the prompt against the style guide first. Defaults to true.
profileNoName of a style profile to enhance against. See list_style_profiles.
publishNoUpload it to Roblox immediately. Defaults to false.
outputPathNoWhere to write the PNG. Defaults to a temp file, whose path is returned.
primaryIndexNoWhich reference to match most closely, counting URLs then paths. Defaults to the first.
referenceUrlsNoPublic image URLs to steer style and subject. The first is treated as the primary reference unless primaryIndex says otherwise.
referencePathsNoLocal image files to use as references. Hosted automatically. At least one reference, by path or URL, is required.
Behavior4/5

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

With no annotations provided, the description carries full disclosure burden. It reveals key side effects (writes to a file, saves to history, can publish to Roblox), the enhancement pipeline, and the dependency on at least one reference image. However, it omits operational details like error behavior, rate limits, or asynchronous execution, making it not fully comprehensive but still quite transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded: the first sentence states the core action, followed by behavioral details and workflow guidance. Each sentence contributes meaning without redundancy, perfectly sized for the tool's complexity.

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?

Given 10 parameters, no output schema, and no annotations, the description covers all critical aspects: purpose, side effects, reference requirement, enhancement behavior, publish option, and a direct alternative. It is highly complete for an agent to select and invoke the tool correctly, with only minor missing details like return format (partially covered by mentioning temp file path).

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 parameters are well-documented. The description adds value by clarifying that despite schema not requiring references, at least one is needed, and explaining the purpose of enhance (style guide rewriting). It also contextualizes primaryIndex and outputPath, enriching the schema's dry definitions.

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?

The description clearly states the tool's purpose: 'Make a new thumbnail image with the site's AI pipeline' and differentiates it from siblings by explicitly contrasting with upload_thumbnail (for publishing) and mentioning history saving. It is specific about the resource (thumbnail image) and the operation (generate), making it unmistakable.

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?

Provides explicit guidance: explains when to use publish (only when agreed on) and advises to generate, look, then call upload_thumbnail otherwise. Also mentions the style-guide rewriting behavior and the reference-image requirement, giving clear context for when to use this tool versus alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Haydebug/whitehat-thumbnails-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server