CutClip.one

shot.generate_keyframe

Generate keyframe image variants for a shot from its camera direction, cast references and location plates. The first variant becomes the start frame if the shot has none. Costs credits per image, charged to the project owner. Runs in the background — poll generation.list.

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": {
      "projectId": "<projectId>",
      "shotId": "<shotId>"
    },
    "name": "shot.generate_keyframe"
  }
}

Input Schema

Name	Required	Description	Default
`model`	No
`shotId`	Yes
`numImages`	No
`projectId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A3.7/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does disclose the two traits that matter most for an agent: credit cost per image billed to the project owner, and asynchronous background execution with polling via generation.list. It does not mention failure/partial-result behavior or what happens to prior keyframes, which keeps it from a 5.

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?

Three tight sentences, front-loaded with the purpose, then the start-frame rule, then the cost and async traits. There is no filler, though the last sentence packs two unrelated facts (credits, polling) into one clause.

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 credit-consuming async generation tool with no annotations and no output schema, the description covers cost, billing target, and polling, which are the hard-to-guess parts. The remaining gap is parameter-level guidance (especially 'model' and the 1-4 variant range), which an agent needs to invoke it correctly.

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

Parameters2/5

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

Schema description coverage is 0% across four parameters, and the description does not explain any of them: projectId and shotId are never tied to billing or scoping, numImages is only obliquely implied by 'variants' and 'per image', and the 'model' parameter is completely undocumented. Only a faint hint at per-image cost scaling is added beyond the schema.

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 and resource ('Generate keyframe image variants for a shot') and names the inputs driving generation (camera direction, cast references, location plates). This clearly separates it from siblings like shot.generate_video, shot.add_still, and shot.select_keyframe.

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

Usage Guidelines3/5

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

It gives one useful conditional ('the first variant becomes the start frame if the shot has none'), which implies when this tool matters. However, it never names alternatives such as shot.add_still for uploading an existing frame or shot.select_keyframe for choosing among variants, so an agent must infer routing.

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

All CutClip.one 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.