Skip to main content
Glama
KyaniteLabs

kinocut

by KyaniteLabs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Crop video frame

video_crop
Destructive

Crop an existing video to a defined rectangle or centered percentage, then render a new output file while leaving the source untouched.

Instructions

Crop an existing video to a rectangular region or centered percentage crop and render a new output file. The source video is read only; x/y default to a centered crop when omitted.

Input Schema

NameRequiredDescriptionDefault
xNoOptional X offset in pixels. Defaults to a centered crop when omitted.
yNoOptional Y offset in pixels. Defaults to a centered crop when omitted.
widthNoCrop region width in pixels. Pair with height unless using crop_percent.
heightNoCrop region height in pixels. Pair with width unless using crop_percent.
overwriteNoExplicitly allow replacing existing media. Existing non-media files are protected.
input_pathYesAbsolute path to an existing local video file. The input file is read only.
output_pathNoDestination video path. Auto-generated when omitted; an existing supplied path may be overwritten.
crop_percentNoCentered crop percentage of original dimensions, such as 50 for the center 50%.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.16.4
    • addedInput schema / properties / overwrite
      Added value: +{
+  "default": false,
+  "description": "Explicitly allow replacing existing media. Existing non-media files are protected.",
+  "title": "Overwrite",
+  "type": "boolean"
+}
  2. Changed1 schema field changedv1.16.0
    • addedInput schema / additionalProperties
      Added value: +false
  3. Changed14 schema fields changedv1.5.1
    • addedInput schema / properties / crop_percent
      Added value: +{
+  "anyOf": [
+    {
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Centered crop percentage of original dimensions, such as 50 for the center 50%.",
+  "title": "Crop Percent"
+}
    • addedInput schema / properties / height / anyOf
      Added value: +[
+  {
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedInput schema / properties / height / default
      Added value: +null
    • addedInput schema / properties / height / description
      Added value: +"Crop region height in pixels. Pair with width unless using crop_percent."
    • removedInput schema / properties / height / type
      Removed value: -"integer"
    • addedInput schema / properties / input_path / description
      Added value: +"Absolute path to an existing local video file. The input file is read only."
    • addedInput schema / properties / output_path / description
      Added value: +"Destination video path. Auto-generated when omitted; an existing supplied path may be overwritten."
    • addedInput schema / properties / width / anyOf
      Added value: +[
+  {
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedInput schema / properties / width / default
      Added value: +null
    • addedInput schema / properties / width / description
      Added value: +"Crop region width in pixels. Pair with height unless using crop_percent."
    • removedInput schema / properties / width / type
      Removed value: -"integer"
    • addedInput schema / properties / x / description
      Added value: +"Optional X offset in pixels. Defaults to a centered crop when omitted."
    • addedInput schema / properties / y / description
      Added value: +"Optional Y offset in pixels. Defaults to a centered crop when omitted."
    • changedInput schema / required
      Previous value: -[
-  "input_path",
-  "width",
-  "height"
-]New value: +[
+  "input_path"
+]
  4. First observedv0.2.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered. The description usefully adds that the source is read only and that a new file is rendered, but it says nothing about overwrite risk or how repeated runs differ, which is the key behavior for a non-idempotent, destructive tool. No contradiction with annotations.

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 sentences, front-loaded with the action and its two modes, with the read-only source note appended. Nothing is redundant or padded.

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

Completeness4/5

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

An output schema exists and annotations cover safety, so the description only needs to frame the operation and its modes, which it does. Minor gap: it doesn't mention that supplying an existing output path may overwrite it, though the schema covers that.

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 description coverage is 100%, so every parameter including x/y defaults, width/height pairing, crop_percent, and overwrite is already documented. The description restates the centered-crop default but adds no new syntax or constraint beyond the schema, so the baseline 3 applies.

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 specific verb+resource ('Crop an existing video') and distinguishes the two supported modes (rectangular region vs centered percentage crop) plus the outcome (new output file). It does not name a sibling such as video_resize or video_apply_mask to sharpen the boundary, 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 only implied: the agent can infer crop-when-you-want-a-subregion, and the note that x/y default to a centered crop gives some operational context. There is no explicit when-to-use vs video_resize/video_apply_mask/video_zoom, and no stated preconditions or exclusions.

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

Deploy Server

Other Tools