Skip to main content
Glama

Retro Diffusion Pixel Art

by ai.retrodiffusion

Create Custom Style

create_user_style

Create a user style from the public RD Pro template using /v1/styles.

Use style_reference_images and style_reference_caption for style-level references. These are baked into the custom style and are not the same as per-inference reference_images.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesDisplay name for the custom style.
min_widthNoForce a fixed width (96-256); must be provided together with min_height.
min_heightNoForce a fixed height (96-256); must be provided together with min_width.
rd_api_keyNoRetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.
style_iconNoIcon name for the style (e.g. 'sparkles').
descriptionNoShort description of the custom style.
force_paletteNoAlways apply palette constraining for this style.
force_bg_removalNoAlways remove backgrounds for this style.
llm_instructionsNoInstructions for the prompt-expansion LLM when this style is used.
reference_imagesNoAlias for style_reference_images on this tool; prefer style_reference_images and never provide both.
reference_captionNoAlias for style_reference_caption on this tool; prefer style_reference_caption and never provide both.
apply_prompt_fixerNoLet the API tidy prompts automatically for this style (default true).
user_prompt_templateNoPrompt template for the style; must contain the {prompt} token.
style_reference_imagesNoStyle-level reference image(s), base64, baked into the custom style (max 1 via the public API).
style_reference_captionNoCaption describing the style reference image(s).
expanded_llm_instructionsNoExtended instructions for the prompt-expansion LLM.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already indicate readOnlyHint=false and destructiveHint=false. The description adds useful behavioral context: style_reference_images are baked into the custom style and are not the same as per-inference reference_images. However, it does not cover authentication requirements, rate limits, or side effects, which are not disclosed by annotations either.

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?

Two sentences and a note, all front-loaded with purpose and key parameter distinctions. No unnecessary words, but the note could be better formatted. Still, it's appropriately concise for a tool with 16 parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (16 parameters) and presence of an output schema, the description covers the most important aspect (style vs inference references) but omits guidance on typical usage flows, required vs optional parameters beyond name, and error handling. It is adequate but not comprehensive.

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 baseline is 3. The description adds significant clarification: distinguishes style_reference_images from inference reference_images, notes the alias parameters should not both be provided, and mentions the max of 1 style reference image via public API. This adds meaning beyond the schema descriptions.

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?

Clearly states the action (create a user style) and the source (public RD Pro template, using /v1/styles). Distinguishes style-level references from per-inference references, which helps differentiate from create_inference. However, it does not explicitly contrast with update_user_style, leaving some ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides no guidance on when to use this tool versus alternatives like update_user_style or start_inference_job. No when-not or prerequisite conditions are mentioned, leaving the agent to infer usage context from the name alone.

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

All Retro Diffusion Pixel Art toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation5/5

Each tool targets a distinct operation: authentication, inference (sync/async/edit), style management, listing, and utility. Even similar tools like create_inference and start_inference_job are clearly differentiated by synchronous vs async execution.

Naming Consistency5/5

All tool names follow the same verb_noun snake_case pattern (e.g., create_inference, get_balance, list_available_styles). No mixed conventions or inconsistent verb forms.

Tool Count4/5

With 19 tools, the count is slightly above the typical 3-15 range, but each tool serves a specific and necessary function for pixel art generation, editing, and management, so it remains well-scoped.

Completeness5/5

The tool set covers the full workflow: authentication, cost estimation, synchronous and async generation, style CRUD, edit tools, pixel fixing, and system status. No obvious gaps for the intended domain.

Resources