Skip to main content
Glama

create_object_pro_flash

Generates a saved pixel-art object from a text description, with optional 8-direction rotation views. Reuse an existing image to reduce generation costs.

Instructions

Create a saved object with the Pro Flash engine in one call: generates a south-facing image from the description and, with n_directions 8, adds v3 rotation views (n_directions 1 = single image). Pass source_image_id or first_frame to reuse an existing image: one-direction finalization is then free and eight views charge only rotations. Objects have no skeleton. Returns a job plus object_id; poll get_job_status for billing_stages, then get_object.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoDisplay name (max 200 chars)
seedNoRecorded seed (default 0); the Pro Flash provider does not promise deterministic output
viewNoCamera view (default 'low top-down')
image_sizeNoSize for text creation. Native sizes: 16x16 (experimental), 24x24, 32x32, 32x48, 64x64, 96x64, 96x96. Custom (Beta): 16-256 per side, both multiples of 4. Defaults to 64x64
descriptionYesObject description (max 2000 chars)
first_frameNoSouth-facing PNG to use instead of generating one. Mutually exclusive with source_image_id
style_imageNoOptional style reference ('left-box' image) whose visual traits are copied into the result. Must fit the operation's native canvas
n_directionsNo1 = single image, 8 = full rotation set (default 8)
style_optionsNoWhich visual traits to copy from style_image (all default true)
source_image_idNoOwned south-facing image ID from a Pro Flash image job — reuses its pixels free of the image charge. Mutually exclusive with first_frame
first_frame_directionNoDirection the supplied/generated first frame faces (default 'south')

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.8.0

TDQS

A4.5/5.0
Behavior5/5

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

No annotations are provided, so the description carries full burden. It discloses the generation process, the optional rotation views, the reuse options with billing implications, the fact that objects have no skeleton, and the return of a job plus object_id with a polling workflow. This is thorough behavioral disclosure.

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?

The description is a single dense sentence but front-loads the main purpose and packs essential details without waste. It could be split into two sentences for readability, but it is efficient and every clause adds information.

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?

Given 11 parameters, nested objects, and no output schema, the description covers the essential workflow: returns job plus object_id, poll get_job_status for billing_stages, then get_object. It also explains billing nuances. It lacks error handling or edge-case descriptions, but for a creation tool this is acceptable.

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 documented. The description adds value by explaining the effect of n_directions (single vs. eight views), the cost implications of reusing source_image_id or first_frame, and the absence of skeleton. These semantics go beyond the schema's individual field descriptions.

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+resource (create saved object with Pro Flash engine), describes the generated south-facing image and optional rotation views via n_directions. Distinguishes from sibling object creation tools by mentioning the Pro Flash engine and v3 rotation views, and notes 'Objects have no skeleton' which separates it from character tools.

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?

Provides clear context on when to use this tool: for creating saved objects with Pro Flash, including reuse of existing images via source_image_id or first_frame. Implies billing advantages of reuse. Does not explicitly name alternatives, but the sibling list suggests create_object_1dir/8dir for simpler cases. The note about skeleton absence guides against using this for characters.

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

Deploy Server

Other Tools