Skip to main content
Glama

Redact sensitive data

snipaya_redact

Finds emails, phone numbers, IBANs, card numbers, tokens, IPs, passwords and faces on-device, then covers them in one undo step using noise, blur, or solid redaction styles.

Instructions

Find emails, phone numbers, IBANs, card numbers, tokens, IP addresses, passwords and faces (on-device) and cover them in one undo step, in the user’s Redaction style (noise by default). style overrides it: noise fills the area with opaque random colors from it, blur pixelates with blocks sized to the text, solid covers it with a plain box. pixelSize sets the noise block size or a coarser minimum for blur. Defaults to every image and category. Returns the ids and counts.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "snipaya_redact"
  }
}

Input Schema

NameRequiredDescriptionDefault
styleNonoise, blur or solid. Defaults to the user’s Redaction setting.
tabIdNoTarget tab id. Defaults to the active tab.
imageIdsNo
pixelSizeNoNoise block size, or minimum blur block size, in canvas units.
categoriesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.2.2
    • addedInput schema / properties / pixelSize
      Added value: +{
      +  "description": "Noise block size, or minimum blur block size, in canvas units.",
      +  "maximum": 400,
      +  "minimum": 4,
      +  "type": "number"
      +}
    • addedInput schema / properties / style
      Added value: +{
      +  "description": "noise, blur or solid. Defaults to the user’s Redaction setting.",
      +  "enum": [
      +    "noise",
      +    "blur",
      +    "solid"
      +  ],
      +  "type": "string"
      +}
  2. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations declare a non-read-only, non-destructive, non-open-world operation, and the description corroborates this by disclosing that the edit lands 'in one undo step' — a genuine reversibility guarantee not found in the annotations. It also flags face detection as on-device and states the return payload (ids and counts). It does not cover failure modes or idempotency, keeping it short of a 5.

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?

The core action is front-loaded in the first clause and every subsequent sentence carries parameter or behavior information. It is dense but slightly run-on, and the style/pixelSize explanations restate what the schema already lists, so it is not maximally tight.

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?

With no output schema, the description correctly states the return value (ids and counts), and it documents all defaults so a zero-argument call is safe. Missing only edge-case behavior (nothing detected, unsupported image) for a tool that mutates user images.

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 coverage is 60%, and the description compensates well for the undocumented parameters: imageIds and categories get an explicit 'Defaults to every image and category' rule, and pixelSize is clarified as 'the noise block size or a coarser minimum for blur', which goes beyond the schema's terser wording. The style enum is also explained functionally (noise/blur/solid behavior).

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?

The opening clause names a specific verb and resource — find listed PII categories plus faces and cover them — and adds the scope details (one undo step, user's Redaction style). No sibling tool in the list performs redaction, so an agent can rule out the other 27 tools immediately.

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 rather than stated: the defaults ('every image and category', active tab) tell the agent it can be called with no arguments, which is useful. But there is no explicit when-to-use/when-not guidance, no prerequisite or permission notes, and no statement about what happens when nothing is detected.

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