Skip to main content
Glama

edit video

edit_video
Destructive

Edit existing footage using a source video and prompt. Creates a separate result and preserves the original clip. For voice-only replacement with unchanged dialogue, use an available speech-to-speech voice-change workflow. Video editing may retain the original voice; reference audio does not guarantee replacement. Inspect the actual output before claiming a changed voice. Use get_model_catalog to choose a supported model and its settings. Returns a tracked task and playable result when complete.

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": {
      "sourceMediaId": "<sourceMediaId>",
      "model": "<model>"
    },
    "name": "edit_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelYesActive model ID supporting this operation. Use get_model_catalog.
promptNoEdit or enhancement instructions.
maxCostUsdNoMaximum charge for each output. Checked against authoritative pricing before generation.
resolutionNo
aspectRatioNo
endFrameUrlNo
mediaInputsNoNamed media slots from get_model_catalog, for example reference_image_uri or mask_url.
scaleFactorNoUpscaling multiplier when supported by the selected model.
sparkTaskIdNoOriginating Spark task for library history and recovery.
workspaceIdNo
modelVariantNoVariant value from get_model_catalog variantSelector.options, such as high for Flare quality. Uses the catalog default when omitted.
outputFormatNoOutput format when supported by the selected model.
generateAudioNoExplicitly enable or disable generated video audio, when supported.
modelSettingsNoModel-specific controls using keys and options from get_model_catalog inputConstraints.slots or variantSelector.
sourceMediaIdYesCompleted workspace source media. The original is preserved.
idempotencyKeyNoStable request key. Retries with the same key reuse the existing output and do not start another paid generation.
sourceImageUrlNoPublic HTTP(S) source image/start-frame URL. Use mediaId for workspace images.
sourceVideoUrlNoPublic HTTP(S) source-video URL.
endFrameMediaIdNoWorkspace image for the final frame, when supported by the selected model.
referenceImagesNoImages to guide generation. Use labels such as person or product and refer to them as @person or @product in the prompt. Each item accepts a workspace mediaId or a public HTTP(S) URL.
sourceImageMediaIdNoWorkspace image to use as the source image/start frame.
sourceVideoMediaIdNoWorkspace video to edit or transform, when supported by the selected model.

Output Schema

NameRequiredDescriptionDefault
dataNo
errorNo
successYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / data / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "aspectRatio": {
      -        "type": [
      -          "string",
      -          "null"
      -        ]
      -      },
      -      "downloadUrl": {
      -        "anyOf": [
      -          {
      -            "format": "uri",
      -            "type": "string"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ]
      -      },
      -      "durationMs": {
      -        "type": [
      -          "number",
      -          "null"
      -        ]
      -      },
      -      "error": {
      -        "type": [
      -          "string",
      -          "null"
      -        ]
      -      },
      -      "imageUrl": {
      -        "anyOf": [
      -          {
      -            "format": "uri",
      -            "type": "string"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ]
      -      },
      -      "mediaId": {
      -        "type": "string"
      -      },
      -      "model": {
      -        "type": [
      -          "string",
      -          "null"
      -        ]
      -      },
      -      "playableUrl": {
      -        "anyOf": [
      -          {
      -            "format": "uri",
      -            "type": "string"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ]
      -      },
      -      "posterUrl": {
      -        "anyOf": [
      -          {
      -            "format": "uri",
      -            "type": "string"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ]
      -      },
      -      "progress": {
      -        "anyOf": [
      -          {
      -            "maximum": 1,
      -            "minimum": 0,
      -            "type": "number"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ]
      -      },
      -      "progressLabel": {
      -        "type": [
      -          "string",
      -          "null"
      -        ]
      -      },
      -      "prompt": {
      -        "type": [
      -          "string",
      -          "null"
      -        ]
      -      },
      -      "status": {
      -        "enum": [
      -          "queued",
      -          "generating",
      -          "completed",
      -          "failed"
      -        ],
      -        "type": "string"
      -      },
      -      "type": {
      -        "enum": [
      -          "image",
      -          "video",
      -          "audio"
      -        ],
      -        "type": "string"
      -      },
      -      "viewUrl": {
      -        "format": "uri",
      -        "type": "string"
      -      },
      -      "workspaceId": {
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "workspaceId",
      -      "mediaId",
      -      "type",
      -      "status",
      -      "progress",
      -      "progressLabel",
      -      "playableUrl",
      -      "imageUrl",
      -      "posterUrl",
      -      "downloadUrl",
      -      "viewUrl",
      -      "durationMs",
      -      "model",
      -      "aspectRatio",
      -      "prompt",
      -      "error"
      -    ],
      -    "type": "object"
      -  },
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "activeIndex": {
      -        "minimum": 0,
      -        "type": "integer"
      -      },
      -      "items": {
      -        "items": {
      -          "$ref": "#/properties/data/anyOf/0"
      -        },
      -        "maxItems": 8,
      -        "minItems": 1,
      -        "type": "array"
      -      }
      -    },
      -    "required": [
      -      "items",
      -      "activeIndex"
      -    ],
      -    "type": "object"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "aspectRatio": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "downloadUrl": {
      +        "anyOf": [
      +          {
      +            "format": "uri",
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "durationMs": {
      +        "type": [
      +          "number",
      +          "null"
      +        ]
      +      },
      +      "elapsedSeconds": {
      +        "anyOf": [
      +          {
      +            "minimum": 0,
      +            "type": "number"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "error": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "heartbeatAgeSeconds": {
      +        "anyOf": [
      +          {
      +            "minimum": 0,
      +            "type": "number"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "height": {
      +        "anyOf": [
      +          {
      +            "exclusiveMinimum": 0,
      +            "type": "number"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "imageUrl": {
      +        "anyOf": [
      +          {
      +            "format": "uri",
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "lastHeartbeatAt": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "mediaId": {
      +        "type": "string"
      +      },
      +      "model": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "playableUrl": {
      +        "anyOf": [
      +          {
      +            "format": "uri",
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "posterUrl": {
      +        "anyOf": [
      +          {
      +            "format": "uri",
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "progress": {
      +        "anyOf": [
      +          {
      +            "maximum": 1,
      +            "minimum": 0,
      +            "type": "number"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "progressLabel": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "prompt": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "requestedAspectRatio": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "status": {
      +        "enum": [
      +          "queued",
      +          "generating",
      +          "completed",
      +          "failed"
      +        ],
      +        "type": "string"
      +      },
      +      "type": {
      +        "enum": [
      +          "image",
      +          "video",
      +          "audio"
      +        ],
      +        "type": "string"
      +      },
      +      "viewUrl": {
      +        "format": "uri",
      +        "type": "string"
      +      },
      +      "width": {
      +        "anyOf": [
      +          {
      +            "exclusiveMinimum": 0,
      +            "type": "number"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "workspaceId": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "workspaceId",
      +      "mediaId",
      +      "type",
      +      "status",
      +      "progress",
      +      "progressLabel",
      +      "playableUrl",
      +      "imageUrl",
      +      "posterUrl",
      +      "downloadUrl",
      +      "viewUrl",
      +      "durationMs",
      +      "model",
      +      "aspectRatio",
      +      "prompt",
      +      "error"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "activeIndex": {
      +        "minimum": 0,
      +        "type": "integer"
      +      },
      +      "items": {
      +        "items": {
      +          "$ref": "#/properties/data/anyOf/0"
      +        },
      +        "maxItems": 8,
      +        "minItems": 1,
      +        "type": "array"
      +      }
      +    },
      +    "required": [
      +      "items",
      +      "activeIndex"
      +    ],
      +    "type": "object"
      +  }
      +]
  2. Changed2 schema fields changed
    • changedInput schema / properties / modelSettings / description
      Previous value: -"Model-specific controls using keys and options from get_model_catalog inputConstraints.slots."New value: +"Model-specific controls using keys and options from get_model_catalog inputConstraints.slots or variantSelector."
    • addedInput schema / properties / modelVariant
      Added value: +{
      +  "description": "Variant value from get_model_catalog variantSelector.options, such as high for Flare quality. Uses the catalog default when omitted.",
      +  "minLength": 1,
      +  "type": "string"
      +}
  3. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Beyond the annotations, it discloses that a new artifact is produced and the source retained, that the returned value is a tracked task with a playable result, and it warns that voice may not actually change, instructing inspection of the output. The voice caveat is genuinely useful context not present in structured fields. There is mild tension with destructiveHint=true given "preserves the original clip," but this reads as a cost/paid-generation side effect rather than a direct contradiction.

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 purpose and non-destructive behavior, then the alternative and the model-selection pointer, then return value. The middle three sentences on voice retention overlap somewhat ("may retain the original voice" / "does not guarantee replacement" / "inspect the actual output"), which could be tightened to one sentence without losing meaning.

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 22-parameter, open-world, paid generation tool with an output schema and full annotations, the description covers the source, the model dependency, side effects and the return contract. Cost behavior (maxCostUsd, paid generation) and retry/idempotency semantics live only in the schema, so a sentence on cost would make it fully complete.

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 coverage is 82%, so the schema already documents nearly all 22 parameters, including the role of model, prompt and the media slots. The description only reiterates the source video, prompt and model-catalog dependency and adds nothing about resolution, scaleFactor, idempotencyKey or the media slot naming convention. Baseline 3 is appropriate.

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?

The description leads with a specific verb and resource ("Edit existing footage using a source video and prompt") and immediately states the key semantic detail that the original clip is preserved and a separate result is created. It also carves out the adjacent voice-replacement case by pointing to a speech-to-speech workflow, so an agent can tell this apart from change_video_voice without opening any 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?

It gives explicit routing guidance: use the speech-to-speech voice-change workflow for voice-only replacement with unchanged dialogue, and use get_model_catalog to pick a model and settings. What's missing is guidance against other close siblings (enhance_video_media, upscale_video, expand_video), so the agent must infer those boundaries.

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.