カーリル for AI

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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is fully covered. The description adds the shape of what can be inspected (name, parent/child, related classifications) but no operational context such as rate limits, auth, or data freshness.

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?

Two compact sentences with the core action front-loaded and no filler. Slightly more could be trimmed, but nothing is wasted.

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?

An output schema exists and annotations carry the safety profile, so the description needn't explain return values or permissions. It is complete enough for a simple single-parameter lookup tool, with only usage routing left unstated.

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 description coverage is 100% and the single ndc_code parameter is fully documented in the schema, including the format examples (000, 007.1, 913.6) and the empty-string-returns-root behavior. The description adds nothing beyond the schema, so the baseline 3 applies.

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?

States a specific verb (取得します/確認できます) and resource (NDC分類情報), and enumerates the retrievable facets: 分類名称, 上位・下位分類, 関連分類. The scope is distinct from the sibling search_books/search_libraries tools, though it never explicitly contrasts itself with them.

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?

Usage is implied — look up classification info from a code — but the description gives no explicit when-to-use, no conditions for choosing it over search_books/search_libraries, and no exclusions. The 'code in, info out' framing is the only guidance offered.

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 declare openWorldHint=true and destructiveHint=false; the description adds operational scope not in the schema, notably the API-key library list and the default behavior when systemids is omitted ('searches all libraries'). readOnlyHint=false is the schema default and does not assert mutation, so it is consistent with a search operation. It does not, however, describe result format, pagination interaction between limit/offset, or rate limits.

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?

Purpose is front-loaded in the first sentence, and the remaining lines are short and purposeful (scope note plus library list). The bulleted list is a slight structural cost but it earns its place by defining valid systemids values.

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?

An output schema exists, so return values need not be explained, and all 11 parameters are covered by the schema. The description supplies the missing operational context (which libraries are reachable and the systemids default), leaving only minor gaps such as pagination semantics.

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 description coverage is 100%, so every one of the 11 parameters is already documented, giving a baseline of 3. The description restates a few of those fields (title, author, publisher, NDC, systemids) but adds no syntax or format detail beyond the schema, so it does not raise the score.

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 gives a specific verb+resource ('図書館の蔵書を検索します' — searches the library collection) and enumerates the searchable fields (title, author, publisher, NDC). It implicitly distinguishes itself from search_libraries (which finds libraries) by focusing on holdings, but it never names or contrasts with a sibling tool explicitly.

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?

It supplies real usage guidance for the systemids parameter — the valid values, the ability to mix in school libraries, and that omitting it searches all libraries. However, it offers no explicit when-to-use-this-vs-alternatives guidance against get_ndc_info or search_libraries, so selection is left to inference.

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?

アノテーションが openWorldHint=true(外部データ参照)と destructiveHint=false を既に示している。説明は『応答単位はシステムで複数の図書館が一つに含まれる』『利用者登録の学校図書館も返す』という返却特性を追加しており付加価値があるが、認証・レート制限や readOnlyHint=false との整合には触れていない。

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?

目的が冒頭に置かれ、システム単位の返却や APIキー制約といった重要情報が簡潔に続く。無駄な文は少ないが、キー制約の一文は構成上やや唐突で、もう少し統合できる余地がある。

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、説明は『システム単位でまとまる』という重要な解釈上の注意を提供している。2パラメータ・低複雑度のツールとして必要な情報はほぼ揃っている。

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?

スキーマ記述カバレッジが100%のため、limit と keyword の意味はスキーマ側で完結している。説明は『図書館名や地域で検索』と keyword の用途を暗示するが、構文や形式の追加情報はなく、ベースライン3が妥当。

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?

明確に動詞(検索)+リソース(図書館)を述べ、目的(蔵書検索に必要なシステムIDの取得)まで示している。search_books との関係にも触れており、兄弟ツールとの区別は概ね可能だが、get_ndc_info との違いには触れていない。

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?

『蔵書検索に必要なシステムIDを取得する』という後続用途(search_books)を暗示しており、利用シーンは推測できる。しかし、いつ search_libraries を search_books の代わりに使うべきか、除外条件や前提は明示されていない。

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