Skip to main content
Glama

Compare images (vision VLM)

compare_images

Compare and validate 2–9 images labeled A, B, C... against a prompt or reference using conformance, refcheck, or rubric modes with selectable VLM slots.

Instructions

2〜9枚の画像を順に Image A, B, C… とラベル付きで送り、比較・照合させる(参照画像×生成候補の突き合わせ・同一仕様での候補比較等)。mode=conformance(既定)は各画像を生成仕様と照合し、refcheck は Image A を正とする参照照合の型を前置する。vlmでVLMスロット(primary/nsfw/fallback)を選べる(既定primary)。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
vlmNo使用するVLMスロット(既定primary。nsfw=R18検査用・未設定項目はprimaryの設定を継承。fallback=通常は失敗時の自動再試行用・明示指定も可)
modeNo検査モード(既定conformance=生成仕様への準拠検査。free=スキャフォールド無し)
promptYes比較・照合の問い(生成仕様の原文・照合観点・意図を明示する)
sourcesYes比較する画像(順序がそのままA, B, C…のラベルになる)
max_tokensNo応答トークン上限(既定4096)
max_long_edgeNoこの呼び出しの長辺上限px(0=無制限。省略=env既定)

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observedv1.4.0

TDQS

B3.3/5.0
Behavior3/5

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

No annotations are provided, so the description must convey behavior. It states that images are sent and compared/verified, implying a read-only analysis, but it does not explicitly mention side effects, data handling, or that it is non-destructive. The absence of any statement about side effects is acceptable for a vision inspection, but not fully transparent.

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 description is concise and well-structured, providing a clear overview of the operation, examples, and mode/vlm specifics in a compact form. It avoids unnecessary filler while still conveying the core functionality.

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?

The description lacks information about the output format or response structure. Since there is no output schema, the description should explain what the tool returns (e.g., a comparison report, pass/fail result, or text explanation). It also does not address error conditions or edge cases (e.g., too many images), making the tool's expected behavior incomplete for an agent.

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?

The schema descriptions already cover all 6 parameters with 100% coverage, including details like order of sources, mode semantics, and vlm slots. The description largely restates this information without adding new meaning beyond what is already in the schema, so it adds marginal value for parameter understanding.

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 description clearly states the tool's purpose: comparing and verifying multiple images, with labels A, B, C… and examples of use cases (reference image × generated candidates, same-spec candidate comparison). It is unambiguous and distinct from a single-image analysis tool.

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?

The description does not explain when to use this tool versus the sibling tool analyze_image. It lacks guidance such as 'use for comparing multiple images, analyze_image for single-image inspection.' The emphasis on modes provides some context but does not explicitly contrast with alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/kjranyone/manga-vision-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server