Skip to main content
Glama

Redact Regions

redact_region
Destructive

Cover specified rectangular regions in videos or screenshots to hide secrets and sensitive on-screen content. Provide pixel coordinates; out-of-frame regions are rejected.

Instructions

Cover given rectangles in a video or screenshot (e.g. secrets on screen). Not automatic detection: find them with find_text redact: true. Off-frame regions are rejected.

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": {
      "input": "<input>",
      "regions": "<regions>"
    },
    "name": "redact_region"
  }
}

Input Schema

NameRequiredDescriptionDefault
padNoGrow each region by this many px (default 0).
colorNoBox fill color (default black).
inputYesPath to the source video or image (png/jpg; time ranges are ignored for an image).
styleNobox (default): irreversible fill; blur/pixelate are partially recoverable.
outputNoOptional output path. Defaults under SCREENCAST_HOME/edits.
regionsYesPixel rectangles (x, y, width, height), each optionally limited to start..end seconds.
overwriteNoAllow replacing an existing file at the output path (default false).

Output Schema

NameRequiredDescriptionDefault
outputPathYesPath of the file written.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.49.1
    • changedInput schema / properties / input / description
      Previous value: -"Path to the source video."New value: +"Path to the source video or image (png/jpg; time ranges are ignored for an image)."
  2. Changed11 schema fields changedv0.47.0
    • changedInput schema / properties / color / description
      Previous value: -"Fill color for box style (default black)."New value: +"Box fill color (default black)."
    • changedInput schema / properties / pad / description
      Previous value: -"Optional pixels to expand each region by, to cover anti-aliased edges (default 0)."New value: +"Grow each region by this many px (default 0)."
    • changedInput schema / properties / regions / description
      Previous value: -"One or more rectangles to redact. Each may be limited to a time window."New value: +"Pixel rectangles (x, y, width, height), each optionally limited to start..end seconds."
    • removedInput schema / properties / regions / items / properties / end / description
      Removed value: -"Optional second to stop redacting after."
    • removedInput schema / properties / regions / items / properties / height / description
      Removed value: -"Region height in pixels."
    • removedInput schema / properties / regions / items / properties / start / description
      Removed value: -"Optional second to start redacting from."
    • removedInput schema / properties / regions / items / properties / width / description
      Removed value: -"Region width in pixels."
    • removedInput schema / properties / regions / items / properties / x / description
      Removed value: -"Left edge in pixels."
    • removedInput schema / properties / regions / items / properties / y / description
      Removed value: -"Top edge in pixels."
    • changedInput schema / properties / style / description
      Previous value: -"box (default) draws an irreversible solid fill; blur and pixelate are softer but partially recoverable."New value: +"box (default): irreversible fill; blur/pixelate are partially recoverable."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": {},
      +  "properties": {
      +    "outputPath": {
      +      "description": "Path of the file written.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "outputPath"
      +  ],
      +  "type": "object"
      +}
  3. First observedv0.32.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds two pieces of non-obvious behavior: that regions must be supplied manually rather than detected, and that off-frame regions are rejected — a validation behavior not visible in annotations. Minor gaps remain around overwrite/irreversibility, but those are handled by the annotations and schema.

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?

Three short clauses, front-loaded with the core action, then the detection alternative, then the validation constraint. No filler and no repetition of schema content.

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, so return values need not be described, and the description covers the two things an agent could most easily get wrong: assuming auto-detection and submitting out-of-bounds rectangles. Adding a note on default output location or irreversibility would make it fully self-sufficient, but the schema already carries those details.

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 the style enum and overwrite flag is already documented in structured data. The description only implicitly touches the regions parameter via the off-frame rejection note and adds no pixel/coordinate or time-range semantics beyond what the schema states. Baseline 3 applies.

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 ('Cover given rectangles in a video or screenshot') with a concrete use case (secrets on screen), and explicitly distinguishes itself from automatic detection by naming find_text. An agent can tell this apart from editing siblings without opening any 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 to find_text with redact: true when detection is needed, which is the key decision point for this tool. It does not discuss when to choose this over other redaction-adjacent workflows (e.g. blur vs box tradeoffs) or prerequisites beyond that, so it falls short of full when/when-not coverage.

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