Skip to main content
Glama

mask

Idempotent

Hide private information in PNG images by covering selected rectangles with black, pixelation, or blur before sharing; returns the edited image.

Instructions

Hide private information in a PNG before sharing it: black, pixelate or blur rectangles. Returns the image.

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": {
      "in": "<in>",
      "regions": "<regions>"
    },
    "name": "mask"
  }
}

Input Schema

NameRequiredDescriptionDefault
inYesPNG path
styleNo
regionsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so safety profile is largely covered. The description usefully adds 'Returns the image' in the absence of an output schema, but leaves a serious ambiguity: whether the input PNG is overwritten in place (consistent with readOnly=false) or a new image is produced, and whether masking is irreversible. That file-mutation question is the single most important behavioral fact for this tool and it is unstated.

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 tight sentence with the action front-loaded and the return behavior appended. Nothing is wasted, though the brevity comes at the cost of the missing mutation and coordinate details noted above.

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 three-parameter image-mutation tool with no output schema, the description covers purpose, styles and the fact that an image comes back, which is a reasonable baseline. It is still incomplete on where the result is written, what happens to the source file, and how region coordinates are interpreted.

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

Parameters2/5

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

Schema coverage is only 33% – only 'in' is documented. The description restates the enum values (black, pixelate, blur) and the notion of 'rectangles', but the schema already encodes both, so it adds almost no new meaning. It never clarifies coordinate units, origin, whether regions may overlap exceed image bounds, or what 'style' defaults to when omitted.

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?

A specific verb-plus-resource ('Hide private information in a PNG') with the three masking styles named, so the agent knows this is a redaction tool rather than a generic image editor. It does not explicitly distinguish itself from the sibling 'crop', which also transforms images, so it falls 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?

'before sharing it' implies the scenario (privacy redaction prior to distribution), but there is no explicit guidance on when to pick this over 'crop' or 'capture', nor any prerequisite or exclusion stated. Usage is inferable but not spelled out.

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