Framevine

Extend video

extend_video

Extend an existing completed video node with a continuation. prompt describes what happens next; pass endNodeId (a completed image node) to steer toward an end frame. 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, plus the parent node it extended so you can confirm it was the right one; poll get_generation_status until it is COMPLETED or FAILED. If the user's intent is ambiguous across branches, call get_thread and ask which node before spending credits.

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": "extend_video"
  }
}

Input Schema

Name	Required	Description
`nodeId`	Yes	Completed video node to extend.
`prompt`	Yes	What happens next in the video.
`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.
`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?

Beyond the annotations (which only declare non-read-only, non-idempotent, non-destructive), the description discloses that the call spends credits, is asynchronous ('returns immediately with a new nodeId and status'), and requires polling to reach COMPLETED or FAILED. This is exactly the operational context annotations cannot convey.

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?

Five tight sentences, front-loaded with the purpose and ending with the safety guardrail on ambiguous intent. Dense but never padded; only minor redundancy with the schema costs it a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, yet the description explains the return shape (new nodeId, status, and the parent node for verification) and the follow-up loop. For a 9-parameter, credit-spending, async mutation that is fully sufficient to invoke correctly.

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%, so the baseline is 3. Most parameter explanation in the description restates the schema verbatim (modelKey from list_models, durationSeconds must be model-supported, endNodeId as an end frame); only the 'steer toward an end frame' nuance for endNodeId adds real meaning.

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 opens with a specific verb and resource ('Extend an existing completed video node with a continuation') and constrains the input to a *completed* node. It does not, however, distinguish itself from the obvious sibling 'edit_video', which an agent could easily confuse with extension, so it falls short of a 5.

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

Usage Guidelines5/5

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

Explicit routing conditions are given for three separate siblings: estimate_cost when unsure about spend, get_generation_status for polling, and get_thread plus a user question when intent is ambiguous. The exclusions ('ask which node before spending credits') are concrete and actionable.

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?