Skip to main content
Glama

Render Clip Chains

lab_verkettung

Render several clips as CHAINS: within a scene one after another (continuity), across scenes in parallel (speed) — the plan follows scene_ref of each job in order. aktion: plan (free: shows the chains) · preis (free: same checks as a real start; returns preis_geschaetzt_credits, preis_hoechstens_credits (with every allowed retry) and reicht against balance, project cap and an active auto run, plus startbilder_offen when a chain's first start image is not approved yet — nothing is created) · starten (COSTS CREDITS, ONLY after the person confirmed the price from aktion=preis). Each clip is charged when it starts; an active lab_auto_lauf cap applies. The FIRST clip of every chain needs an approved start image (keyframe checkpoint, as in lab_animate) unless ohne_keyframe; later clips derive from the chain. Sending starten twice returns the running chain (wiederverwendet: true) instead of paying twice. Transition between clips of a chain (uebergang): schnitt (default) = hard cut to a NEW camera angle — the next clip does NOT start from the last frame; its prompt begins with the previous clip's end state (wardrobe, props, place, light), characters and location come from each job's own character_refs/location_id. A schnitt follow-up clip is TEXT-TO-VIDEO: without character_refs/location_id the person and place hang on one sentence of text — give them for real continuity. CONTINUITY CHECK: in a chain with more than one clip every clip is checked against its prompt BEFORE the next one starts (status pruefen, wartet_auf: abgleich while the check runs — that is not a hung job). On mismatch the clip is re-rendered at most neuversuche times (default 1, prompt led by the failed claims, charged like the clip); if it still deviates the chain STOPS before the next clip is paid (chain status abgebrochen, clip status abweichung, issues and verworfen at the clip). The last clip of a chain gets its retry too but the chain then ends fertig with the verdict at the clip. Single clips are only checked in the background. durchgehend = the last frame becomes the start image — only for one unbroken take. Follow a started chain with lab_get_job(job_id): result.zusammenfassung (laeuft/fertig/abgebrochen), result.ketten (status and grund per chain) and result.clips (keyed by clip index: video_id, status, fehler_klasse). Job status done only means nothing runs any more — check result.zusammenfassung.abgebrochen before reporting success. A failure stops only its own chain. Dispatch rule: continuous scene → one chain with schnitt; one unbroken motion → a single clip ≤ 15 s, else durchgehend; separate scenes, time jumps, costume changes or montage → separate scenes (parallel). Over ~3 minutes total: suggest narrowing the scope first.

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": {
      "aktion": "<aktion>",
      "project_id": "<project_id>",
      "jobs": "<jobs>"
    },
    "name": "lab_verkettung"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobsYesOne entry per clip, IN ORDER — the same fields as lab_animate (prompt, scene_ref, tool, duration_seconds, resolution, character_refs, location_id, source_image_id, nur_eigene_daten …). nur_eigene_daten is per clip and follows the rule of lab_animate. Each prompt: For a clip of 4 s or longer, write the action as timed beats, one per line under a '// Action Timing' header: '[0-2s] [CAM 01] <framing> -> [ACT] <action> -> [DIAL] <who>: "<line>" -> [AUDIO] <sound>'. The spans start at 0 and cover duration_seconds; keep the same CAM number while the camera does not cut. lab_prompt_transform (medium video) writes exactly this form. Murnau's SceneFlow lights each beat while the clip plays, and the crew judges it there. scene_ref decides the chains: consecutive clips with the same scene_ref chain, a clip without scene_ref stands alone.
modusNohybrid (default): chain within scenes; parallel: every clip alone; sequenziell: one chain over everything
aktionYesplan and preis are free; starten costs credits
uebergangNoTransition at each cut inside a chain; default schnitt
project_idYesProject id (from lab_list_projects)
neuversucheNoRetries per clip after a failed continuity check: 1 (default) or 0 (stop at the first deviation). Name preis_hoechstens_credits to the person before starten.
ohne_keyframeNoSkip the keyframe checkpoint on purpose. By default a paid clip only starts from a start image the user has approved (lab_review_asset verdict: accepted) — look at the frame first, then spend on the clip. Set true only when the user explicitly asked to skip the frame check.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / jobs / description
      Previous value: -"One entry per clip, IN ORDER — the same fields as lab_animate (prompt, scene_ref, tool, duration_seconds, resolution, character_refs, location_id, source_image_id …). Each prompt: For a clip of 4 s or longer, write the action as timed beats, one per line under a '// Action Timing' header: '[0-2s] [CAM 01] <framing> -> [ACT] <action> -> [DIAL] <who>: \"<line>\" -> [AUDIO] <sound>'. The spans start at 0 and cover duration_seconds; keep the same CAM number while the camera does not cut. lab_prompt_transform (medium video) writes exactly this form. Murnau's SceneFlow lights each beat while the clip plays, and the crew judges it there. scene_ref decides the chains: consecutive clips with the same scene_ref chain, a clip without scene_ref stands alone."New value: +"One entry per clip, IN ORDER — the same fields as lab_animate (prompt, scene_ref, tool, duration_seconds, resolution, character_refs, location_id, source_image_id, nur_eigene_daten …). nur_eigene_daten is per clip and follows the rule of lab_animate. Each prompt: For a clip of 4 s or longer, write the action as timed beats, one per line under a '// Action Timing' header: '[0-2s] [CAM 01] <framing> -> [ACT] <action> -> [DIAL] <who>: \"<line>\" -> [AUDIO] <sound>'. The spans start at 0 and cover duration_seconds; keep the same CAM number while the camera does not cut. lab_prompt_transform (medium video) writes exactly this form. Murnau's SceneFlow lights each beat while the clip plays, and the crew judges it there. scene_ref decides the chains: consecutive clips with the same scene_ref chain, a clip without scene_ref stands alone."
  2. Changed1 schema field changed
    • changedInput schema / properties / jobs / description
      Previous value: -"One entry per clip, IN ORDER — the same fields as lab_animate (prompt, scene_ref, tool, duration_seconds, resolution, character_refs, location_id, source_image_id …). scene_ref decides the chains: consecutive clips with the same scene_ref chain, a clip without scene_ref stands alone."New value: +"One entry per clip, IN ORDER — the same fields as lab_animate (prompt, scene_ref, tool, duration_seconds, resolution, character_refs, location_id, source_image_id …). Each prompt: For a clip of 4 s or longer, write the action as timed beats, one per line under a '// Action Timing' header: '[0-2s] [CAM 01] <framing> -> [ACT] <action> -> [DIAL] <who>: \"<line>\" -> [AUDIO] <sound>'. The spans start at 0 and cover duration_seconds; keep the same CAM number while the camera does not cut. lab_prompt_transform (medium video) writes exactly this form. Murnau's SceneFlow lights each beat while the clip plays, and the crew judges it there. scene_ref decides the chains: consecutive clips with the same scene_ref chain, a clip without scene_ref stands alone."
  3. Changed1 schema field changed
    • addedInput schema / additionalProperties
      Added value: +false
  4. Changed1 schema field changed
    • addedInput schema / properties / neuversuche
      Added value: +{
      +  "description": "Retries per clip after a failed continuity check: 1 (default) or 0 (stop at the first deviation). Name preis_hoechstens_credits to the person before starten.",
      +  "maximum": 1,
      +  "minimum": 0,
      +  "type": "integer"
      +}
  5. Added

TDQS

A4.8/5.0
Behavior5/5

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

Far exceeds the annotations: it discloses cost behavior (each clip charged at start, retry 'charged like the clip'), a duplicate-call rule returning wiederverwendet: true instead of double charging, the keyframe approval prerequisite, the continuity-check state machine (pruefen / wartet_auf / abweichung / abgebrochen) and its stop-before-next-payment semantics, plus the trap that job status done does not imply success. There is a mild tension with idempotentHint=false given the double-submit dedupe, but it does not contradict readOnlyHint or destructiveHint and is best read as partial, not full, idempotency.

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 concept is front-loaded and almost every clause carries real information, but the whole definition is one dense run-on block with no line breaks or bullets, mixing German and English mid-sentence. Several items are restated from the input schema (uebergang default, ohne_keyframe approval rule, neuversuche default), so a portion of the text does not earn its place beyond structured fields.

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?

Although there is no output schema, the description supplies the return shape explicitly (result.zusammenfassung with laeuft/fertig/abgebrochen, result.ketten with status and grund, result.clips keyed by clip index with video_id/status/fehler_klasse) and names the follow-up tool lab_get_job. For a 7-parameter, cost-incurring orchestration tool this is essentially complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so 3 would be the baseline, but the description goes well beyond it: it explains that jobs are ordered and that scene_ref is what actually decides chain membership, that neuversuche must be named to the person as preis_hoechstens_credits, that ohne_keyframe is an explicit user-authorized skip, and what schnitt versus durchgehend mean at the frame level. These are semantic rules the schema cannot express.

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 ('Render several clips as CHAINS'), then immediately defines the two chaining axes (sequential within a scene, parallel across scenes) and the three actions. It is clearly distinguished from single-clip rendering by the explicit note that 'Single clips are only checked in the background' and by referencing lab_animate only as the field-compatibility baseline.

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?

Gives an explicit dispatch rule ('continuous scene → one chain with schnitt; one unbroken motion → a single clip ≤ 15 s, else durchgehend; separate scenes … → separate scenes (parallel)'), gates the paid action on a prior aktion=preis confirmation, and adds a scope guard ('Over ~3 minutes total: suggest narrowing the scope first'). Alternatives and exclusion conditions are named, not implied.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources