Skip to main content
Glama

video_edit

Edit a recorded app video timeline by updating scenes, reordering or removing clips, adding assets, and adjusting captions, transitions, zoom, and sound.

Instructions

Edit the timeline. ops is a list of: {op:"update", scene, duration?, speed?, title?, subtitle?, transition?("slide"|"fade"|"zoom"|"rise"|"none"), side?("left"|"right": caption side for this scene in landscape; the phone glides across the frame when it changes), focus?(element label | {x,y,w,h} dp | null), zoom?(1-3), zoomTimes?([inStart,inEnd,outStart,outEnd] recording seconds, for recordings), scroll?(0-1 | false), callouts?, popouts?} {op:"move", scene, to(number|"first"|"last") | before | after} · {op:"remove", scene} · {op:"add", asset, at?} · {op:"drop", asset} (discard a bad capture) {op:"settings", format?, appName?, tagline?, cta?, captionSide?("left"|"right"), sound?{sfx: bool, volume: 0-1}, theme?{accent, bg:[c1,c2]}} · {op:"plan", targetSeconds?} scene = id ("s3"), 1-based position, or a screen name/route ("dashboard").

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": {
      "ops": "<ops>"
    },
    "name": "video_edit"
  }
}

Input Schema

NameRequiredDescriptionDefault
opsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It does disclose some real semantics — the phone glides across the frame when caption side changes, `drop` discards a bad capture, `zoomTimes` applies only to recordings, `focus: null` clears focus. But it says nothing about whether edits are atomic, whether ops apply in order, what happens when a `scene` id doesn't resolve, or whether an edit can be undone.

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?

Front-loaded with the only thing that matters — the op grammar — and compressed with `·` separators and optional-field `?` markers rather than prose. It is dense and slightly cryptic (`callouts?`, `popouts?` are named but never specified), but for a DSL of this size almost every line earns its place.

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 mutation tool with a single opaque nested parameter, no annotations, and no output schema, the description covers the input grammar well but is thin on everything else. Undefined sub-schemas for `callouts`, `popouts`, `asset`, and `focus` labels, plus the absence of any error or result behavior, leave an agent guessing at exactly the parts most likely to cause a failed call.

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

Parameters5/5

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

Schema coverage is 0% — the schema only says `ops` is an array of objects with a string `op` — so the description does all the work, and it does a lot: it enumerates every op (`update`, `move`, `remove`, `add`, `drop`, `settings`, `plan`), the fields each accepts, enum values for transition and caption side, the zoom range 1-3, and three accepted forms for `scene` (id, 1-based position, or route name). This is meaning far beyond what any structured field provides.

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?

Opens with a specific verb+resource: "Edit the timeline", then immediately defines the `ops` payload. An agent knows it mutates an existing video timeline rather than capturing or rendering one. It never names a sibling (video_plan, video_timeline, video_render), so differentiation is left to inference.

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

Usage Guidelines2/5

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

There is no when-to-use / when-not-to-use guidance, no prerequisites (must a capture or plan exist first?), and no mention of alternatives among the many video_* siblings. The op list explains what can be expressed, not when this tool is the right call, so any routing decision has to come from outside the definition.

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