AV女優判定AI

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

readOnlyHint=trueというアノテーションに加え、「画像は判定後すぐに破棄され保存されない」「認証コードは30分有効・最大10回利用可能」という運用上の重要情報が説明されている。アノテーションだけでは分からない認証要件やデータ保持ポリシーを追加で開示しており、安全性の理解に貢献している。

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

目的、認証要件、データ破棄ポリシーという重要な情報が順序立てて1段落にまとめられており、冗長な表現がない。全体として簡潔でありながら必要な情報が欠落していない。

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

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

出力スキーマが存在するため戻り値の説明は不要であり、認証フロー、利用制限、データライフサイクルまで含めて、このツールを正しく呼び出すために必要な情報が全て揃っている。複雑な認証依存型ツールとして十分に完成度が高い。

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

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

スキーマのパラメータ説明が既に100%網羅されており、画像形式・サイズ制限・data URLの許容などが詳細に記載されている。ツール説明は認証コードの必要性を強調しているが、パラメータの意味自体はスキーマの情報を補完する以上の付加価値を提供していない。

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

「画像から出演AV女優の候補を類似度が高い順に返す」と、動詞・対象・出力形式が明確に定義されている。姉妹ツールの「search」と異なり、画像入力に基づく判定であることが明示されており、区別が可能。

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

認証コードが無い場合の案内手順と、コードの有効期限・利用回数制限が具体的に示されており、利用条件が明確。ただし、姉妹ツール「search」との使い分けや代替手段については言及がなく、排他的な利用条件は示されていない。

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

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

Annotations already provide readOnlyHint=true, so the read-only nature is covered. The description adds useful behavioral context beyond that: no authentication required, exact actress-name matches return an actress page, and result URLs point to this site's work/actress pages. This is helpful without contradicting the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is four short, information-dense sentences. It front-loads the database scope and search capability, then adds the exact-match exception, authentication note, and URL behavior. Every sentence earns its place with no filler or redundancy.

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

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

For a 3-parameter search tool with a full output schema and readOnly annotation, the description covers everything an agent needs to invoke it correctly: query scope, floor options, exact-match behavior, authentication requirements, and result URL semantics. The pagination limit and floor code meanings are already present in the input schema, so no critical gaps remain.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds extra semantics by explaining what kinds of queries are valid (title, product number, manufacturer, actress name), the exact-match behavior, and the database coverage behind the 'floor' parameter. These details go beyond the raw schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb (keyword search), a concrete resource (the AV actress identification AI database over three named stores), and enumerates the searchable fields: title, product number, manufacturer, and actress name. It also distinguishes itself by noting the exact-match actress-page behavior, which helps separate it from identify_actress even though that sibling is not named.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context for when to use the tool: any keyword search across the specified database, with optional floor filtering. It does not explicitly say when not to use it or compare it to identify_actress, so it falls short of the top score, but the supported use cases are sufficiently clear.

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