Framevine

Image to video

image_to_video

Animate an existing completed image node into a video. The node is used as the start frame; pass endNodeId (another completed image node) to interpolate between two frames. modelKey comes from list_models (a video model) and durationSeconds must be one that model supports. Spends credits; use estimate_cost first if unsure. Returns immediately with a new nodeId and status; poll get_generation_status until it is COMPLETED or FAILED.

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": {
      "threadId": "<threadId>",
      "nodeId": "<nodeId>",
      "prompt": "<prompt>",
      "modelKey": "<modelKey>",
      "durationSeconds": "<durationSeconds>"
    },
    "name": "image_to_video"
  }
}

Input Schema

Name	Required	Description
`nodeId`	Yes	Completed image node to use as the start frame.
`prompt`	Yes	How the image should move.
`modelKey`	Yes	Video model key from list_models.
`threadId`	Yes	Thread containing the node.
`endNodeId`	No	Optional completed image node to use as the end frame (interpolation).
`resolution`	No	Resolution. Defaults to 480p.
`aspectRatio`	No	Aspect ratio. Defaults to auto.
`sourceFileIds`	No	Optional extra input image file ids.
`durationSeconds`	Yes	Clip length in seconds; must be supported by the model.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations only declare the non-read-only, non-idempotent, non-destructive profile; the description adds the behavior that actually matters — it spends credits, returns immediately with a new nodeId and status, and requires polling get_generation_status until COMPLETED or FAILED. The new-node-per-call flow is consistent with idempotentHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five compact sentences in a deliberate order: what it does, frame interpolation, input sourcing, cost caution, then the async return/poll contract. Nothing redundant or padded.

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?

Compensates for the missing output schema by describing the return (nodeId plus status) and the polling loop clearly. The one remaining gap is sourceFileIds, an optional multi-image parameter with no mention anywhere in the description.

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 100%, and the schema already documents nodeId as the start frame, endNodeId as the end frame, modelKey from list_models, and durationSeconds as model-dependent. The description restates these relationships rather than adding new semantics (e.g. it says nothing about sourceFileIds or duration/model limits). Baseline 3 applies when the schema does the heavy lifting.

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+resource ("Animate an existing completed image node into a video") and pins the distinguishing constraint: it needs a completed image node as a start frame, which separates it from generate_video/extend_video/edit_video siblings. An agent can route to it without opening the 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?

Gives clear operational context: modelKey comes from list_models, durationSeconds must be model-supported, and callers should use estimate_cost first when unsure. It does not explicitly say when to prefer this over generate_video or extend_video, so the sibling exclusions are implied rather than stated.

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

All Framevine 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.

Resources

Need Help?