Skip to main content
Glama

clip_ai

Apply Studio AI and tracking operations to timeline clips, including Magic Mask creation and regeneration, stabilization, smart reframe, color cache toggling, and sidecar updates.

Instructions

Studio AI/tracking ops on timeline clips. action: magic_mask (mode F|B|BI; needs a Magic Mask in the node — creates one on the current node), magic_mask_regenerate, stabilize, smart_reframe (uses timeline aspect, e.g. vertical), color_cache_on/off, update_sidecar.

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": {
      "clips": "<clips>",
      "action": "<action>"
    },
    "name": "clip_ai"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoBI
clipsYes
actionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations at all, the description carries the full burden. It does disclose one important side effect: magic_mask 'creates one on the current node' if absent, which signals a write operation rather than a pure read. It says nothing about whether these operations modify or render the clip, how long stabilize/reframe take, whether they are undoable, or what a caller gets back.

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?

One dense, front-loaded block with no filler; the operation list is compact and scannable. It is telegraphic to the point of being cryptic in places ('needs a Magic Mask in the node'), but nothing is wasted.

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 3-parameter, annotation-free, output-schema-free tool that triggers heavy renders, the definition covers the action vocabulary and one prerequisite but omits the 'clips' parameter entirely and gives no sense of result, timing, or reversibility. Adequate to start a call, not adequate to call it confidently.

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

Parameters4/5

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

Schema description coverage is 0%, so the description must compensate, and it largely does: it enumerates every action value and constrains mode to F|B|BI in the context of magic_mask. Gaps remain — the letters F/B/BI are never expanded, and the required 'clips' parameter is never explained (count, type, or shape).

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?

States a concrete verb class and resource: 'Studio AI/tracking ops on timeline clips', and then enumerates the concrete operations. An agent knows exactly which capabilities live here (magic mask, stabilize, smart reframe, color cache, sidecar). It does not, however, contrast with the sibling media_ai to distinguish clip-level from media-level AI work, so it stops 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 Guidelines3/5

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

Usage is implied through the enumerated action values and a key precondition ('needs a Magic Mask in the node'), which is genuinely useful context for choosing action=magic_mask. But there is no explicit when-to-use vs. when-not, and no pointer to media_ai for media-level equivalents, leaving the agent to infer the boundary.

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