Skip to main content
Glama

update_edit

Update an existing edit (project). Supports partial updates — only provided fields are changed.

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": {
      "workspaceId": "<workspaceId>",
      "editId": "<editId>"
    },
    "name": "update_edit"
  }
}

Input Schema

NameRequiredDescriptionDefault
styleNoOne short sentence describing only the visual aesthetic shared by every shot (e.g., "cinematic noir, dramatic lighting, subtle film grain"). Do not include characters, locations, props, actions, or shot-specific details.
titleNoNew title for the edit
editIdYesThe edit ID to update
videoModelNoDefault model ID for shot video generations
aspectRatioNoDefault aspect ratio for new media
speechModelNoDefault model ID for speech generation. Defaults to Cartesia Sonic 3.6 (cartesia-sonic-3-6) for new edits.
transitionsNoComplete replacement list of timeline transition boundary objects. Use fromShotId/toShotId for robust adjacency-based transitions.
workspaceIdYesThe workspace ID
styleAssetIdsNoLegacy array of explicitly supplied style-reference asset IDs. Routine projects use the edit.style text and should leave this unset.
shotImageModelNoDefault model ID for shot still/image generations
sceneImageModelNoDefault model ID for scene/location image generations
defaultImageModelNoDefault model ID for new image generations. Also updates shotImageModel, sceneImageModel, and characterImageModel unless those are provided separately. Defaults to google-nano-banana-2-1 for new edits.
defaultVideoModelNoDefault model ID for new video generations. Also updates videoModel unless videoModel is provided separately. Defaults to google-gemini-omni-1-2 for new edits.
characterImageModelNoDefault model ID for character image generations

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / speechModel / description
      Previous value: -"Default model ID for speech generation. Defaults to ElevenLabs V4 Speech (elevenlabs-tts-v4) for new edits."New value: +"Default model ID for speech generation. Defaults to Cartesia Sonic 3.6 (cartesia-sonic-3-6) for new edits."
  2. Changed1 schema field changed
    • changedInput schema / properties / defaultVideoModel / description
      Previous value: -"Default model ID for new video generations. Also updates videoModel unless videoModel is provided separately. Defaults to google-gemini-omni-1-1 for new edits."New value: +"Default model ID for new video generations. Also updates videoModel unless videoModel is provided separately. Defaults to google-gemini-omni-1-2 for new edits."
  3. Changed1 schema field changed
    • changedInput schema / properties / speechModel / description
      Previous value: -"Default model ID for speech generation. Defaults to Cartesia Sonic 3.5 (cartesia-sonic-3-5) for new edits."New value: +"Default model ID for speech generation. Defaults to ElevenLabs V4 Speech (elevenlabs-tts-v4) for new edits."
  4. Changed1 schema field changed
    • changedInput schema / properties / defaultImageModel / description
      Previous value: -"Default model ID for new image generations. Also updates shotImageModel, sceneImageModel, and characterImageModel unless those are provided separately. Defaults to google-gemini-3-image for new edits."New value: +"Default model ID for new image generations. Also updates shotImageModel, sceneImageModel, and characterImageModel unless those are provided separately. Defaults to google-nano-banana-2-1 for new edits."
  5. 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 carries the full disclosure burden. It usefully explains that this is a partial update where only supplied fields change, which is a real behavioral trait. It omits other important traits: whether transitions is a full replacement (destructive to existing boundaries), the cascading side effects of defaultImageModel/defaultVideoModel, permission requirements, and whether updates are reversible.

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?

Two short sentences, front-loaded with the action and immediately followed by the most important behavioral qualifier. There is no filler; the only mild redundancy is the parenthetical "(project)" gloss.

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 14-parameter mutation tool with no annotations and no output schema, the description is minimal but the schema is fully self-documenting, which limits the gap. Still, nothing is said about what is returned, permission/ownership requirements, or the destructive replacement behavior of the transitions array, so an agent must infer those from parameter descriptions.

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

Parameters3/5

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

Schema description coverage is 100%, so all 14 parameters, including the cascading defaultImageModel/defaultVideoModel semantics and the style vs. styleAssetIds distinction, are already documented in the schema. The description adds no parameter-level meaning beyond what the schema provides, so the baseline of 3 applies.

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 ("Update an existing edit") and clarifies that an edit is a project, which disambiguates the domain vocabulary. It does not distinguish this from siblings like create_edit or get_edit, but the read/write intent is unmistakable.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no mention of prerequisites (workspaceId/editId are required), and no exclusions or pointer to alternatives such as create_edit for new projects or update_scene/update_shot for nested resources. The only usage-adjacent statement is the partial-update note, which describes behavior rather than selection criteria.

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.