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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false, so the agent knows it is a non-destructive external write. The description adds that files are sent to rokadoc and converted to structured text, but omits critical behavior such as whether the operation is asynchronous and requires polling via get_conversion_result.

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?

A single sentence that is front-loaded with the core action and resource, with no redundant wording. It is appropriately sized for the essential information it conveys.

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 conversion tool with five parameters, no output schema, and siblings for listing conversions and retrieving results, the description is missing crucial workflow context. It does not explain that the conversion may be asynchronous or that results are fetched via get_conversion_result, leaving the agent without enough information to invoke it correctly in a pipeline.

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 all five parameters (file_path, from_page, to_page, space_id, space_name) are already documented in the input schema. The description adds no extra meaning about page ranges, space selection, or precedence rules.

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 (変換する) and resource (ドキュメントファイル) and names the external service (rokadoc), so an agent can tell what the tool does. It does not distinguish this from siblings like get_conversion_result or list_conversions, so it falls short of a 5.

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?

There is no guidance on when to use this tool versus alternatives (e.g., list_conversions, get_conversion_result). It implies a conversion context but offers no explicit conditions, prerequisites, or workflow routing.

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 readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, covering the safety profile. The description adds nothing behavioral — it does not say what happens if the conversion is still running, whether it blocks or polls, or what the retrieved result contains.

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?

A single front-loaded sentence with zero waste, appropriate for a simple retrieval tool. It is efficient, though the brevity contributes to the gaps noted in other dimensions.

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?

With no output schema, the description carries the burden of explaining the return value — job status, artifacts, or error states when a job is incomplete or failed — and says none of that. For a result-retrieval tool this is a meaningful omission, though the annotations do cover the safety profile.

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 space_id, space_name and conversion_id are already documented in the schema, including the precedence rule for space_id. The description adds no syntax, format, or ID-source detail beyond that, 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) and resource (変換ジョブの結果) with clear scope — the result of one conversion job. It does not, however, explicitly distinguish itself from siblings such as list_conversions or convert_document, so it stops short of a 5.

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?

There is no guidance on when to use this tool versus convert_document (to start a conversion) or list_conversions (to enumerate jobs). The agent must infer the workflow position from the name alone.

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 readOnlyHint=true、idempotentHint=true、destructiveHint=false、openWorldHint=true を宣言しており、安全性プロファイルは既にカバーされている。説明文はそれを超える情報（ページネーション、返却件数、認可要件など）を一切追加しておらず、付加価値が乏しい。

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?

一文のみで無駄な表現はないが、簡潔さというよりは情報不足に近い。前置きもなく端的ではあるが、その短さが有益な文脈を犠牲にしている。

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?

読み取り専用の一覧取得ツールでアノテーションが安全性をカバーしているものの、出力スキーマが存在しないため、返却される内容（ジョブの状態や形式）を説明する必要がある。説明文はそれに応えておらず、エージェントが呼び出し結果を正しく解釈するための情報が不足している。

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% であり、space_id / space_name の意味や「space_id 指定時は space_name を無視」という優先順位はスキーマ側で完全に説明されている。説明文はパラメータに言及しておらず、スキーマ以上の意味を追加していないため、ベースラインの 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?

「変換ジョブの一覧を取得する」は明確な動詞（取得する）とリソース（変換ジョブの一覧）を示しており、何をするかは即座に分かる。ただし、get_conversion_result や convert_document といった兄弟ツールとの違いには一切触れておらず、差別化はされていない。

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?

いつ使うべきか、いつ使うべきでないか、あるいは代替ツール（get_conversion_result など）との使い分けについての言及が一切ない。リスト取得という用途は名前から推測できるが、説明文による誘導は存在しない。

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 cover the safety profile (readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true). The description adds that the search is RAG-based, which gives useful context about retrieval semantics, but it does not disclose result format, ranking behavior, or other operational constraints beyond 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 a single front-loaded sentence with no wasted words. While extremely concise, it is arguably undersized for a tool with five parameters and no output schema, but the sentence itself earns its place.

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?

There is no output schema, so the description should ideally explain what RAG search returns (e.g., document passages or ranked results), but it does not. It also lacks usage context relative to sibling conversion tools, leaving meaningful gaps for an agent trying to select and interpret the tool.

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 the input schema already documents all five parameters including query, tags, space_id, space_name, and max_results. The description adds no additional parameter semantics beyond what the schema provides, so the baseline score of 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 and resource: execute RAG search against documents registered in rokadoc. The resource 'documents' differentiates it from the conversion-oriented siblings. However, it does not explicitly contrast itself with alternatives such as convert_document or list_conversions.

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?

No guidance is given on when to use this tool versus alternatives, nor on prerequisites or exclusions. The only implied usage is that it searches documents, which is already evident from the name.

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