Skip to main content
Glama

Generate image or video

generate

Starts Brennglas image or video render jobs from a chosen workflow and source images, then waits for the result and returns a preview or job ID for later retrieval.

Instructions

Starts a job in Brennglas (it appears live in the user's gallery). Pick the workflow from list_models. images: gallery ids or absolute file paths; the first is the main/start image, further ones are references (for first+last frame video, the second is the last frame). Waits up to wait_seconds, then returns the result with a preview image, or the id to pass to wait. Videos take 30 s to several minutes. Camera moves in image to video (LTX): large moves (arc, orbit, crane, drone, bullet time) only show from about 5 s; with 3 s the model falls back to a gentle push-in. For those use duration >= 5 and either pe=true or a detailed prompt that also describes the camera path.

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": {
      "workflow": "<workflow>"
    },
    "name": "generate"
  }
}

Input Schema

NameRequiredDescriptionDefault
aspectNoScene format with figures, e.g. "16:9" (default), "9:16", "4:5"
imagesNoGallery ids, "upload:…" refs from last_frame, or absolute paths of local image files
paramsNoField values by key, see list_models
promptNoPrompt text; English works best
figuresNoFigure names or ids (see figures): new scene with these characters/products on an empty canvas; needs an edit workflow, prompt = the scene only, images become further references
workflowYesWorkflow name, e.g. "zimage-t2i", "ltx25-i2v", "wan22cam-i2v"
wait_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden, and it discloses real behavior: the job appears live in the user's gallery (a visible side effect), a blocking wait up to wait_seconds, the return shape (preview image or id for wait), and expected latency (videos take 30 s to several minutes). It also warns about model fallback for short-duration camera moves. It does not mention cost/credits or failure behavior.

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 action and output shape, then the image-ordering rule, then latency and the camera-move caveat. Dense and mostly waste-free, though the camera-move sentence is long and slightly run-on, and mixes a niche LTX-specific caveat into the core description.

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 7-parameter, nested-object generation tool with no output schema, the description covers the essential flow: workflow selection, image roles, blocking vs. polling return, and latency expectations. Gaps remain around the free-form params object and figures behavior, which the schema covers only partially.

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 high (86%), so the baseline is 3, but the description adds ordering semantics the schema does not convey: the first image is the main/start frame and later images are references, with the second acting as the last frame. It also ties workflow choice to list_models and explains the pe/duration interaction, adding genuine meaning beyond the schema text.

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 ("Starts a job in Brennglas") and clarifies the job produces images or video via a named workflow. It also names the sibling tools that bookend it (list_models for workflow selection, wait for polling), so an agent can distinguish it from gallery, wait, and list_models without opening a schema.

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?

Gives explicit routing: choose the workflow from list_models, and either accept the waited result or pass the returned id to wait. It also adds a conditional guideline for camera-move videos (use duration >= 5 with pe=true or a detailed camera path). Lacks an explicit when-not-to-use statement or guidance on when to prefer wait_seconds=0.

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