openFlow

edit_video

Rewrite a video from a plain description: "make the sky stormy", "take the passer-by out of the shot", "warmer light", "put the product from the image on the table".

Source — ONE of:
  media_id: id from a previous generate_video* result (OUR OWN generation). Job is
            pinned to the account that produced it.
  video_base64: base64-encoded YOUR OWN clip (mp4/mov/avi/3gp, up to 60s/1GB).
                Worker uploads it via Flow's Scotty resumable upload (reversed via
                Flow Web Ingredients, 2026-10-14) onto a healthy account, then runs
                the edit on that account. The upload itself costs no credits.

start_sec / end_sec: edit only this piece of the source (both or neither, at most
10 s). The result is ONLY that piece — not the full clip with the piece replaced.
reference_images_base64: up to 5 raw base64 images (no data: prefix); the object in
the image is put into the clip — say in the prompt what to do with it.

20 credits per edit (abra_edit_360p: 10). Not a mask tool — describe the change and
where it goes ("on the left", "in the sky"); mask/style image types are not honored.

Prompt template that lands best — fill each part, one or two sentences each:
  Goal: what changes ("Replace the man on the left with the character from image 1").
  Source: "The source video drives camera, motion, timing and lip movement."
  Reference: what to take from each image ("use only the character's look; ignore
    the image background").
  Scene: describe the room/background in words (helps the model keep it intact).
  Keep: "Everything else stays exactly as in the source."
  Timing: "The new character inherits the exact movement and position of the one
    it replaces, from the first frame to the last."
Draft on abra_edit_360p (10 credits) to check the edit lands, then run abra_edit; the
seed does not carry an edit take across resolutions, so the final can differ in details.
Only edit footage the user owns or is licensed to use; do not put real people's
likeness into clips without their consent.

Input Schema

Name	Required	Default
`seed`	No
`aspect`	No	VIDEO_ASPECT_RATIO_LANDSCAPE
`prompt`	Yes
`end_sec`	No
`media_id`	No
`start_sec`	No
`video_base64`	No
`include_preview`	No
`video_model_key`	No	abra_edit
`reference_images_base64`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 15, 2026

addedInput schema / properties / seed

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Seed"
+}

Changed3 schema fields changedOct 15, 2026

addedInput schema / properties / end_sec

Added value: +{
+  "anyOf": [
+    {
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "End Sec"
+}

addedInput schema / properties / reference_images_base64

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Reference Images Base64"
+}

addedInput schema / properties / start_sec

Added value: +{
+  "anyOf": [
+    {
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Start Sec"
+}

Changed5 schema fields changedOct 14, 2026

addedInput schema / properties / media_id / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / media_id / default
```
Added value: +null
```
removedInput schema / properties / media_id / type
```
Removed value: -"string"
```

addedInput schema / properties / video_base64

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Video Base64"
+}

changedInput schema / required

Previous value: -[
-  "prompt",
-  "media_id"
-]New value: +[
+  "prompt"
+]

First observedSep 1, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only give readOnly/destructive/openWorld flags; the description adds real substance — credit costs (20, 10 for 360p), the upload mechanism via Flow's Scotty resumable upload, the 10-second span limit, that the result is ONLY the piece, that it's not a mask tool and mask/style image types are not honored, and that seed detail may not carry across resolutions. This is exactly the extra context annotations don't supply.

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-loads the purpose and examples, then organizes source/piece/reference/credits/template in scannable blocks. The prompt template is long but earns its place for this model. Minor: the Scotty/Web Ingredients parenthetical reads as internal jargon that an agent doesn't need.

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?

A 10-parameter, no-output-schema, mutation tool; the description covers source selection, span limits, reference images, costs, and the model-key workflow. Gaps are small (seed behavior partially covered, aspect/include_preview unmentioned) and no return-shape explanation is strictly needed since the tool implies a video result, but a line on output would help.

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 0%, so the description must carry parameter meaning and it does: media_id vs. video_base64 semantics and constraints (mp4/mov/avi/3gp, 60s/1GB), start_sec/end_sec must be both or neither and at most 10s, reference_images_base64 up to 5 raw base64 with no data: prefix, prompt template guidance. Only seed, aspect, include_preview, and video_model_key are unmentioned.

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 (rewrite/edit) plus resource (video) and gives four concrete example prompts showing the kind of transformation. It is clearly differentiated from siblings like generate_video, recast_video, and extend_video because the examples all describe modifications to existing footage.

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?

Explicitly says a source is required and lists the two mutually exclusive source types (media_id from a previous generate_video result vs. own video_base64). Gives credit costs and a draft-on-360p-then-final workflow. It doesn't contrast against recast_video or extend_video, which would be the natural alternatives to name.

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

All openFlow tools Inspect

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.

edit_video

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources