CutClip.one

shot.draft

Draft a shot list for one scene — shot sizes, angles, movement, lens, f-stop, focus — from the scene, the film look and the cast (metered in credits unless the owner uses their own Anthropic key). Returns drafts only; create the ones you want with shot.create.

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>",
      "sceneId": "<sceneId>"
    },
    "name": "shot.draft"
  }
}

Input Schema

Name	Required	Description	Default
`count`	No
`sceneId`	Yes
`guidance`	No
`projectId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations, the description carries the burden and does disclose two non-obvious behaviors: output is non-persistent drafts, and generation is metered in credits unless the owner supplies their own Anthropic key. It does not disclose default draft count, latency, or what a draft object looks like, but the cost and side-effect profile are the material facts here.

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?

Two tight sentences with zero filler: the purpose and content list come first, then the persistence and cost caveats. The parenthetical about the Anthropic key is the only aside and it earns its place by changing the cost model.

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?

No annotations and no output schema, so the description must cover behavior and return shape — it does well on both (drafts, not persisted) but leaves the count and guidance parameters undocumented and never indicates the default number of drafts returned. Adequate for a call, but an agent would still have to guess on two inputs.

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, so the description must compensate and largely does not. It implies sceneId/projectId via 'for one scene' and gestures at guidance through 'from the scene, the film look and the cast', but says nothing about the 'count' parameter (1–8) or what 'guidance' should contain (max 1000 chars). Two of four parameters remain opaque.

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 ('Draft a shot list for one scene') and enumerates exactly what the drafts cover (sizes, angles, movement, lens, f-stop, focus). It also names the sibling it is not — drafts are created via shot.create — so the agent can separate it from shot.create without opening either 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?

Explicitly routes the agent: this tool only produces drafts, and shot.create is the path to persist them. It also flags the cost condition (credits unless the owner uses their own Anthropic key), which affects whether to call it. It stops short of stating when drafting is unnecessary (e.g. if shots already exist), so it is not a full when/when-not pair.

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.