Server Quality Checklist

Tool Scores

• jp_browse_onomatopoeiaA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare read-only and non-destructive. The description adds meaningful context: pagination behavior (limit/offset/has_more), the return structure, and guidance to consult jp_list_onomatopoeia_categories for valid category IDs.

  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?

  Well-structured with summary, args, returns, and examples. Bilingual repetition adds some length but each section serves a distinct purpose, keeping it focused and skimmable.

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

  Completeness5/5

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

  Covers filtering, pagination, return fields, parameter constraints, and category lookup. With an explicit output schema snippet and examples, no critical gaps remain for an agent to invoke correctly.

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

  Parameters4/5

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

  Schema has 100% coverage with enums and descriptions. The description adds value by explaining how to obtain category IDs via a sibling tool and providing concrete natural-language to parameter examples, which goes beyond the schema.

  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?

  Description uses specific verbs ('Browse', '取得する') and clearly defines scope: filtering by category and/or linguistic type with pagination. It distinguishes from sibling tools like jp_search_onomatopoeia by focusing on list browsing rather than keyword search.

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

  Usage Guidelines4/5

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

  Provides examples mapping natural language requests to parameters ('擬情語だけ見たい' -> type='gijougo'), establishing clear usage context. Does not explicitly exclude alternatives or mention when not to use, but the browsing vs. searching distinction is implicit.

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

• jp_list_onomatopoeia_categoriesA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the exact return structure (JSON with total_entries and categories) and an example, providing useful behavioral context 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.

  Conciseness4/5

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

  The description is concise and front-loaded with the English summary, followed by Args, Returns, and an example. The bilingual duplication is acceptable for the tool's audience, and no unnecessary sentences are present.

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

  Completeness5/5

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

  For a simple, read-only list tool, the description is complete. It includes the return format, an example usage, and annotations cover safety. The low complexity and presence of output schema (in description) make this fully sufficient.

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

  Parameters5/5

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

  There are zero parameters, and the description explicitly states 'Args: なし' (none). The input schema confirms no properties, and no further parameter explanation is needed.

  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 explicitly states 'List all available categories with the number of entries in each', which is a specific verb+resource action. It clearly distinguishes itself from sibling tools (search, explain, browse, random) by focusing on category listing.

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

  Usage Guidelines4/5

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

  The description provides a clear context for use ('どんな種類のオノマトペが入ってる?' example) and states that no arguments are needed. It does not explicitly mention when not to use or alternatives, but the purpose is unambiguous and distinct from sibling tools.

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

• jp_random_onomatopoeiaA
  4.5/5.0
  Behavior4/5

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

  Annotations already cover readOnly and non-destructive behavior. The description adds transparency by stating the random nature, count range (1-10), category filtering, and the return structure. It also provides example category 'taste', giving a peek into expected behavior.

  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?

  The description is compact and well-organized with clear sections for Args, Returns, and Examples. It front-loads the core purpose and avoids unnecessary filler, making it easy to scan and apply.

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

  Completeness5/5

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

  For a simple two-parameter tool with annotations and an output schema, the description covers everything needed: purpose, parameter constraints, return format, and usage examples. It is complete without being verbose.

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

  Parameters4/5

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

  Schema coverage is 100%, but the description reinforces parameter semantics with concrete examples (e.g., '食感の語で3問クイズ' -> count=3, category='taste') and states defaults. This adds meaningful interpretive guidance beyond the schema.

  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 states 'ランダムにオノマトペを取り出す' (pick random onomatopoeia entries) and provides concrete use cases like quizzes and daily-word features. This clearly identifies the tool as a random selection utility, distinct from siblings like search or explain.

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

  Usage Guidelines4/5

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

  It specifies useful contexts ('daily-word features and quizzes') and gives example queries that map to parameter values. However, it does not explicitly mention when to use search or browse tools instead, so it lacks explicit alternatives/exclusions.

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

• jp_explain_onomatopoeiaA
  4.6/5.0
  Behavior5/5

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

  The description discloses the return format (found boolean, entry structure with fields, message) and error behavior (found=false when not in dictionary). It goes beyond the annotations by describing the not-found fallback and example input formats, which aids the agent in predicting tool behavior.

  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 well-structured with clear sections: intro, args, returns, examples, and error handling. It is slightly verbose due to bilingual repetition, but every section serves a purpose and the front-loaded English explanation makes the core function immediately clear.

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

  Completeness5/5

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

  Given the tool's simplicity (one parameter) and the presence of an output schema, the description fully covers usage: what to pass, what to expect in the return object, and how to handle failures. The examples and error handling make it complete for an agent to invoke correctly.

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

  Parameters4/5

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

  The input schema already fully describes the 'word' parameter with min/max length and a concise description. The description's Args section adds value by providing example values ('しんしん', 'shinshin') and clarifying that both kana and romaji are accepted, which enriches the schema's baseline meaning.

  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 function: explaining the meaning, category, example, and nuance of a specific Japanese onomatopoeia. The verb 'explain' and resource 'specific Japanese onomatopoeia' distinguish it from siblings like jp_search_onomatopoeia, which is used for searching when a word is not found.

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

  Usage Guidelines4/5

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

  The description includes an 'Error Handling' section that explicitly instructs the agent to use jp_search_onomatopoeia when the word is not in the dictionary. It also provides examples of input patterns, implying the tool is for explaining known onomatopoeia. However, it does not explicitly contrast its use with other siblings like jp_browse or jp_random.

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

• jp_search_onomatopoeiaA
  4.6/5.0
  Behavior4/5

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

  Annotations already cover read-only/idempotent/non-destructive behavior. The description adds valuable behavioral context beyond that: query language flexibility, a defined return structure with a message field for empty results, and an example showing query normalization ('雨が静かに降る' -> '雨 静か 降る'). This is more than baseline but not exhaustive.

  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 well-structured with sections for Args, Returns, Examples, and exclusions. It repeats the main purpose in Japanese and English, which is somewhat redundant but serves bilingual users and is not bloated. Every section earns its place.

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

  Completeness5/5

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

  The tool has a clear search use case, an output schema that covers the return structure, annotations for safety, a sibling-tool cross-reference for edge cases, and concrete examples. The description is complete for an agent to select and invoke the tool correctly.

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

  Parameters4/5

  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 meaningful examples for the query parameter, a cross-reference for obtaining valid category values via jp_list_onomatopoeia_categories, and reiterates the limit range. This goes beyond the schema's own descriptions.

  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: 'Search Japanese onomatopoeia by scene, meaning, or keyword' and explicitly notes bilingual query support. It also differentiates from the sibling tool jp_explain_onomatopoeia via the 'Don't use when' note, making the scope unambiguous.

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

  Usage Guidelines5/5

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

  The description provides explicit guidance on when NOT to use the tool and points to the correct alternative: 'Don't use when: 特定の語の意味だけを知りたい場合は jp_explain_onomatopoeia を使う'. It also includes concrete examples of valid query phrasings, making usage clear.

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