Skip to main content
Glama

image_compare

Compare two images pixel by pixel to report percent differing, PSNR, a change bounding box, and a diff image.

Instructions

Pixel-compare two images: % differing, PSNR, change box, diff 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": {
      "a": "<a>",
      "b": "<b>"
    },
    "name": "image_compare"
  }
}

Input Schema

NameRequiredDescriptionDefault
aYes
bYes
resizeNo
out_dirNo
thresholdNo0-255

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.2

TDQS

C2.9/5.0
Behavior3/5

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

Annotations only supply destructiveHint=false, so the description carries most of the burden. It does disclose the return content (% differing, PSNR, change box, diff image), which is valuable since there is no output schema, but it omits whether a diff image is written to disk, supported input formats, and cost on large images.

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?

A single front-loaded line with no wasted words. The telegraphic output list is efficient, though slightly terse at the cost of clarity about what each output item means.

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

Completeness2/5

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

With 5 parameters at 20% schema coverage and no output schema, the definition should explain input types (a/b), the resize and out_dir behavior, and where the diff image lands. Instead it only enumerates result metrics, leaving the majority of the calling contract undocumented.

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 description coverage is only 20% — just threshold (0-255) is documented — so a, b, resize, and out_dir have no explanation anywhere. The description adds nothing about them; only the phrase "diff image" faintly hints that out_dir receives written output, leaving the agent to guess what a and b are (paths vs URLs) and what resize does.

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?

"Pixel-compare two images" gives a specific verb and resource, and the output list (% differing, PSNR, change box, diff image) further pins down what the tool produces. It is clearly distinct from image_edit or media_info, though it never acknowledges the generic sibling "diff" or explains how it differs from a plain file diff.

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 explicit when-to-use or when-not-to-use guidance, and no mention of alternatives such as diff or image_edit. The pixel-level framing implies a use case, but the agent must infer it rather than being told.

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