Skip to main content
Glama

shot.create

Add a shot to a scene with camera direction (§38). Each shot gets its own video clip on the timeline; the scene's length becomes the sum of its shots and later clips ripple. The first shot of a scene takes over the scene's existing video placeholder.

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": {
      "projectId": "<projectId>",
      "expectedVersion": "<expectedVersion>",
      "sceneId": "<sceneId>"
    },
    "name": "shot.create"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedNo
orderNoPosition within the scene (default: last)
actionNoWhat happens during the shot (used for video)
cameraNoPhysical camera settings. Unset fields are left to the model.
sceneIdYes
dialogueNoSpoken line(s); prefix with the speaker's name ("ANNA: …") so shot.lipsync knows who says it
lightingNo
shotSizeNo
projectIdYes
locationIdNoOverride the scene's location for this shot (null = where the scene is)
videoModelNo
aspectRatioNoThis shot's frame shape (null = the film look's, else the project's). Stills use it; the video take follows its start frame
cameraAngleNo
compositionNoe.g. "rule of thirds, subject frame left, negative space right"
descriptionNoWhat the frame shows
characterIdsNoCast members in frame — their reference images keep them consistent
generateAudioNoAsk the video model for native audio (costs more)
cameraMovementNo
expectedVersionYes
videoResolutionNoVideo output resolution (null = the model's default; only some models offer a choice, and higher costs more)
plannedDurationMsNo
speakerCharacterIdNoWho speaks the dialogue (null = the character it names, else the first cast member with a voice)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description does real work by disclosing non-obvious side effects: the scene length becomes the sum of shots, later clips ripple, and the first shot absorbs the scene's placeholder. It omits other consequential behavior — expectedVersion conflict handling, whether generation is triggered or costs credits, and what is returned — so it does not fully carry the burden of an unannotated mutation tool.

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?

Three short sentences, front-loaded with the core action and followed by timeline consequences and the placeholder rule; every sentence contributes. The '(§38)' spec reference is minor noise that means nothing to an agent.

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?

For a 22-parameter, no-annotation, no-output-schema creation tool, the description covers purpose and timeline effects but leaves error/version behavior, generation side effects, and return value unaddressed. It is adequate to select the tool but thin for invoking it correctly.

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

Parameters2/5

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

With 22 parameters at 55% schema coverage, the description should compensate for undocumented fields, yet it only alludes to camera direction and never explains order, dialogue/speaker linkage, characterIds, generateAudio cost, or version semantics. Nearly all parameter meaning it could add is left to the schema, and a substantial gap across 22 params remains unfilled.

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?

The description gives a specific verb and resource ('Add a shot to a scene') plus the key attached capability ('with camera direction'), which is enough to separate it from shot.update or shot.draft. Sibling differentiation is only implicit — it does not state why to create rather than update an existing shot — but the verb/resource pair is unambiguous.

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

Usage Guidelines3/5

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

Usage is implied: you call this to create a new shot inside an existing scene, and the note about the first shot taking over the placeholder hints at the empty-scene case. There is no explicit 'use this instead of X' routing to shot.update, shot.reorder, or timeline.add_placeholder, so the agent must infer alternatives.

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.