Skip to main content
Glama
Sign In

FilmLab

by com.thefilmradar
OverviewDiscussionsAdmin

Prompt Transform

lab_prompt_transform
Idempotent

Turn a loose idea into a production-ready image or video prompt — the same Dreamer engine the FilmLab web UI uses (modes: beautify, storyboard, polish, format, shorten, expand, simplify, custom, stiluebernahme). beautify GENERATES (a 50-character thought comes back as a full prompt); polish/format/shorten/expand/simplify PRESERVE what is there. medium=video plus depth=skeleton yields the 15-block production prompt; depth only applies to video. anlass only applies to beautify. custom and stiluebernahme require instruction. For video the answer carries clip_duration_seconds — hand THAT number to lab_animate(duration_seconds), otherwise a prompt timed to 12s gets rendered as lab_animate's 5s default. In an Apps-capable host this opens as a form you can adjust and re-run; elsewhere it answers with the prompt as plain text. Pass tool (the registry key you will hand to lab_animate/lab_generate) and the finished prompt is laid out in the skeleton of that model family — location, camera, lens and light land where that family reads them, worded the way it reads them; families without a measured rule keep them appended as before, and the answer says so (prompt_skelett).

Input Schema

NameRequiredDescriptionDefault
modeNoDefault beautify (generates). beautify: Aus der Idee einen vollständigen Prompt bauen — ergänzt Licht, Optik, Kamera, Stimmung | storyboard: Szene in 4–8 nummerierte Panels zerlegen — je Panel ein eigenständiger Bild-Prompt | polish: Wortwahl polieren, Flow verbessern, Redundanz entfernen — Länge bleibt | format: In // Subject // Lighting // Camera Sektionen ordnen, Wortlaut bleibt | shorten: ~30% kürzer, jedes Wort muss Gewicht tragen | expand: Texturen, Lichtreflexe, atmosphärische Details | simplify: Direkt und klar, weniger Fachjargon | custom: Eigene Anweisung — z.B. 'Mach es düsterer' | stiluebernahme: Licht, Optik und Look aus einer Beschreibung — Motiv und Bildaufbau bleiben wörtlich
toolNoOptional: the model you will render with, as the registry key from lab_list_models. Decides which family skeleton lays out camera, lens and light — and whether it is a measured rule or the plain appended form.
depthNovideo only: sketch (5 blocks, default) or skeleton (15 blocks)
anlassNobeautify only: what the image is FOR. Default frei
mediumNophoto (default) or video — decides the section layout
promptYesThe text to work on — a loose thought is enough for beautify
winkelNoOptional: change the camera angle of the EXISTING prompt — a key such as augen, unter, auf, vogel, frosch, schraeg, ots, pov, profil. Implies mode=custom and needs no instruction; combinable with groesse.
familieNoOptional, instead of tool: the model family by name when no registry key is at hand. Medium decides whether the image or the video skeleton applies.
groesseNoOptional: change the shot size of the EXISTING prompt, keeping subject, light and place — a key such as ews, ws, mws, ms, mcu, cu, ecu, macro. Implies mode=custom and needs no instruction. An unknown key is rejected with the known ones.
kontextNoOptional, for mode beautify: the scene and earlier shots, for continuity only. Characters, objects and places named here stay the same; only the prompt itself is depicted.
technikenNoUp to three directing technique keys from lab_regie_techniken. Their prompt fragments are appended verbatim after the transform, ordered angle, framing, composition, movement. One angle and one movement at most; movement only with medium=video.
project_idNoOptional: the project this prompt is for. With tool or familie, its Lens Lab optics, Pose Director framing and gaffer light are laid into the prompt. If the project has look_in_post on and a Lens Lab set chosen, grain, halation, vignetting, chromatic aberration and edge softness are left out — the FilmLab Look plugin adds them in Resolve; the answer lists what was removed.
referenzenNoThe references the prompt may point at, IN THE ORDER you will pass them to lab_animate/lab_propose. Write @bild1, @video1, @ton1 in your prompt and they come back as the markers the model actually reads (@Image1, @Video2, @Audio1) — the reference clip itself is @Video1, so the first video reference is @Video2. A mention with no matching reference is rejected instead of being left in the text, where it would reach the model as a word.
instructionNoRequired for custom (an order, e.g. 'make it darker') and stiluebernahme (a style description)
location_idNoOptional, only with tool or familie: the location board whose prompt prefix becomes the place block — the same board you will hand to lab_animate/lab_generate.
projektstilNoOptional, with project_id: the Dreamer writes under the project's style kit and look, as in the app. Without it the project only decides the look_in_post filter.
duration_secondsNovideo only: the clip length in seconds the ACTION TIMING beats are written to. Default 5 (what lab_animate renders without an explicit duration). Rejected for medium=photo.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / kontext
      Added value: +{
+  "description": "Optional, for mode beautify: the scene and earlier shots, for continuity only. Characters, objects and places named here stay the same; only the prompt itself is depicted.",
+  "maxLength": 1500,
+  "type": "string"
+}
    • addedInput schema / properties / projektstil
      Added value: +{
+  "description": "Optional, with project_id: the Dreamer writes under the project's style kit and look, as in the app. Without it the project only decides the look_in_post filter.",
+  "type": "boolean"
+}
  2. Changed1 schema field changed
    • changedInput schema / properties / project_id / description
      Previous value: -"Optional, only with tool or familie: the project whose Lens Lab optics, Pose Director framing and gaffer light should be laid into the prompt."New value: +"Optional: the project this prompt is for. With tool or familie, its Lens Lab optics, Pose Director framing and gaffer light are laid into the prompt. If the project has look_in_post on and a Lens Lab set chosen, grain, halation, vignetting, chromatic aberration and edge softness are left out — the FilmLab Look plugin adds them in Resolve; the answer lists what was removed."
  3. Changed1 schema field changed
    • addedInput schema / additionalProperties
      Added value: +false
  4. Changed2 schema fields changed
    • addedInput schema / properties / groesse
      Added value: +{
+  "description": "Optional: change the shot size of the EXISTING prompt, keeping subject, light and place — a key such as ews, ws, mws, ms, mcu, cu, ecu, macro. Implies mode=custom and needs no instruction. An unknown key is rejected with the known ones.",
+  "type": "string"
+}
    • addedInput schema / properties / winkel
      Added value: +{
+  "description": "Optional: change the camera angle of the EXISTING prompt — a key such as augen, unter, auf, vogel, frosch, schraeg, ots, pov, profil. Implies mode=custom and needs no instruction; combinable with groesse.",
+  "type": "string"
+}
  5. Changed1 schema field changed
    • changedInput schema / properties / anlass / enum
      Previous value: -[
-  "frei",
-  "interview",
-  "szene",
-  "portrait",
-  "street",
-  "editorial"
-]New value: +[
+  "frei",
+  "interview",
+  "szene",
+  "portrait",
+  "street",
+  "editorial",
+  "handy"
+]
  6. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations are minimal (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description carries the real behavioral load: beautify GENERATES while polish/format/shorten/expand/simplify PRESERVE, the host-dependent Apps-form vs plain-text response, rejection of unmatched @-mentions, and the look_in_post filter that strips grain/halation/vignetting with the answer listing removals. These are exactly the non-obvious traits an agent cannot infer from annotations.

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

Conciseness3/5

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

The core purpose is front-loaded, but the body is a dense em-dash-chained block that restates mode names and medium/depth rules already present in the schema. Information density is high, yet a reader must parse one long paragraph to extract the conditional rules.

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 17-parameter tool with no output schema, the description does the necessary work: it names key response fields (clip_duration_seconds, prompt_skelett, the removed-effects list) and explains reference-marker rewriting. It does not fully describe the response shape or the storyboard mode's output, leaving a modest gap.

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 the baseline is 3; the description earns above that by adding cross-parameter interaction rules not obvious from per-field text — depth gated on medium=video, anlass gated on beautify, instruction required for custom/stiluebernahme, and tool/familie selecting the skeleton family. The mode list itself is largely repeated from the enum description.

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?

States a specific verb and resource: 'Turn a loose idea into a production-ready image or video prompt' via the Dreamer engine, and enumerates the modes. It also clarifies the downstream relationship to lab_animate/lab_generate. It does not differentiate itself from the similarly named sibling lab_transform, which leaves one plausible ambiguity unresolved.

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 concrete conditional guidance: 'depth only applies to video', 'anlass only applies to beautify', 'custom and stiluebernahme require instruction', and 'medium=video plus depth=skeleton yields the 15-block production prompt'. It also routes the agent forward ('hand THAT number to lab_animate(duration_seconds)'). It stops short of stating when to choose this over siblings such as lab_transform.

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

All FilmLab toolsInspect
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