Skip to main content
Glama

Compare Web Screenshots

compare_web_screenshots
Idempotent

Compare two self-verifying PNG screenshot artifacts locally to return exact changed-pixel ratios and channel deltas without OCR or external services.

Instructions

Compare two self-verifying PNG screenshot artifacts with local pixel metrics. Returns exact changed-pixel ratios and channel deltas without OCR or external services.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "after": {
        "bytes": 70,
        "sha256": "153cf6c9a526a63053a37b10234c2fd85df38887c2dc0a800d90abfa6631d01c",
        "media_type": "image/png",
        "data_base64": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mP8/5+hHgAHggJ/PzWvWQAAAABJRU5ErkJggg=="
      },
      "before": {
        "bytes": 70,
        "sha256": "153cf6c9a526a63053a37b10234c2fd85df38887c2dc0a800d90abfa6631d01c",
        "media_type": "image/png",
        "data_base64": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mP8/5+hHgAHggJ/PzWvWQAAAABJRU5ErkJggg=="
      },
      "channel_threshold": 0
    },
    "name": "compare_web_screenshots"
  }
}

Input Schema

NameRequiredDescriptionDefault
afterYesThe later or right-hand observation to compare.
beforeYesThe earlier or left-hand observation to compare.
channel_thresholdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare idempotentHint=true, destructiveHint=false, and openWorldHint=false, so safety and locality are partly covered. The description corroborates locality ('local pixel metrics', 'without external services') and hints that artifacts are integrity-checked ('self-verifying'), but it never explains what happens when dimensions differ, what errors look like, or how the sha256 fields are validated.

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 tight sentences with no filler. The core action and the numeric nature of the result are front-loaded, and the negative constraints (no OCR, no external services) are packed into a single efficient clause.

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 only three parameters, a 67% schema coverage, and no output schema, the definition is close to sufficient: it names the inputs' nature and the shape of the return values (ratios and per-channel deltas). It falls short only on threshold semantics and mismatch/failure behavior, which an agent would still have to discover by calling.

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 67%: before/after carry their own descriptions ('earlier or left-hand' / 'later or right-hand'), but channel_threshold is an undocumented 0-255 integer with default 0. The description never mentions the threshold or how it affects the reported deltas, so the one gap in the schema is not compensated for. 'Self-verifying' weakly implies the sha256/bytes fields are checked rather than merely passed through.

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?

The description states a specific verb and resource (compare two PNG screenshot artifacts) plus the method (local pixel metrics) and output form (changed-pixel ratios, channel deltas). It does not, however, distinguish itself from siblings such as compare_web_captures or compare_artifacts, which read as near neighbors.

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 by the object being compared ('two self-verifying PNG screenshot artifacts'). The 'without OCR or external services' clause acts as a soft boundary for what this tool will not do, but there is no explicit when-to-use versus the other compare_* tools and no stated prerequisites.

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