Server Quality Checklist

Tool Scores

• miyabi__analyze_task_intentC
  2.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool analyzes and classifies tasks but doesn't describe how it behaves—e.g., whether it's read-only, if it has rate limits, what permissions are needed, or what the output format looks like. This leaves significant gaps in understanding the tool's operational traits.

  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 a single, efficient sentence that directly states the tool's purpose without any wasted words. It is front-loaded and appropriately sized for its function, making it highly concise and well-structured.

  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?

  Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what the analysis returns (e.g., classification results or confidence scores), behavioral aspects like error handling, or how it integrates with sibling tools. For a tool with no structured metadata, more contextual detail is needed to be fully helpful.

  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 input schema has 100% description coverage, with the 'prompt' parameter fully documented. The description doesn't add any extra meaning beyond the schema, such as examples or format details, but since the schema does the heavy lifting, the baseline score of 3 is appropriate for adequate parameter semantics.

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

  Purpose4/5

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

  The description clearly states the tool's purpose: 'analyze user tasks and determine whether they are development-related or general tasks.' It uses specific verbs ('analyze,' 'determine') and identifies the resource ('user tasks'). However, it doesn't explicitly differentiate from sibling tools like 'miyabi__auto_dispatch' or 'miyabi__handle_development_task,' which might have overlapping functions, so it doesn't reach the highest score.

  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 provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, exclusions, or compare it to sibling tools such as 'miyabi__auto_dispatch' or 'miyabi__handle_development_task,' leaving the agent to infer usage context without explicit direction.

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

• miyabi__generate_articleC
  2.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions '生成します' (generates) and features like 'LLMO対策、サムネイル指示付き', but fails to describe critical behavioral traits such as whether this is a read-only or mutative operation, potential side effects (e.g., if it creates persistent content), authentication needs, rate limits, or output format. This leaves significant gaps in understanding how the tool behaves.

  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, stating the core purpose in a single sentence. It efficiently includes key features without unnecessary elaboration. However, it could be slightly more structured by separating the main action from additional features for clarity.

  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?

  Given the complexity of an 8-parameter tool with no annotations and no output schema, the description is incomplete. It lacks details on behavioral traits, usage context, and output expectations. While the schema covers parameters well, the description doesn't compensate for the absence of annotations or output schema, making it inadequate for fully understanding the tool's operation.

  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?

  Schema description coverage is 100%, so the input schema already documents all 8 parameters with descriptions. The tool description adds no additional meaning about parameters beyond what's in the schema. According to the rules, when schema coverage is high (>80%), the baseline score is 3 even without param info in the description, which applies here.

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

  Purpose4/5

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

  The description clearly states the tool's purpose: '医療AI関連の学術記事を生成します' (generates academic articles related to medical AI). It specifies the domain (medical AI) and output type (academic articles), though it doesn't explicitly differentiate from sibling tools like 'miyabi__analyze_task_intent' or 'miyabi__handle_development_task', which appear to serve different functions. The mention of 'LLMO対策、サムネイル指示付き' (LLMO countermeasures, with thumbnail instructions) adds specificity about features.

  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 provides no guidance on when to use this tool versus alternatives. It doesn't mention any prerequisites, exclusions, or scenarios where other tools might be more appropriate. Without such context, users must infer usage based on the tool's name and description alone, which is insufficient for optimal selection.

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

• miyabi__handle_development_taskC
  2.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. While it mentions the two-step workflow (Issue creation → Agent execution), it doesn't clarify critical aspects such as permissions required, whether the operation is destructive or read-only, expected response format, error handling, or rate limits. For a tool that creates issues and executes agents, this is a significant gap in transparency.

  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, consisting of a single sentence that directly states the purpose and workflow. There's no unnecessary verbiage, and every part of the sentence contributes to understanding the tool's function. However, it could be slightly more structured by separating the workflow steps more clearly.

  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?

  Given the complexity of a tool that creates issues and executes agents, with no annotations and no output schema, the description is incomplete. It doesn't explain what the tool returns, how errors are handled, or any behavioral nuances. The agent is left with significant gaps in understanding how to use this tool effectively in practice.

  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 input schema has 100% description coverage, with 'prompt' described as '開発タスクの内容' (content of the development task) and 'projectPath' as 'プロジェクトのパス（オプション）' (project path, optional). The description doesn't add any meaningful semantics beyond what the schema already provides. According to the rules, with high schema coverage (>80%), the baseline is 3 even without extra param info in the description.

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

  Purpose4/5

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

  The description clearly states the tool's purpose: '開発タスクを処理します（Issue作成→Agent実行）' which translates to 'Process development tasks (Issue creation → Agent execution)'. This specifies the verb ('process') and resource ('development tasks'), and outlines the two-step workflow. However, it doesn't explicitly differentiate from sibling tools like 'miyabi__analyze_task_intent' or 'miyabi__auto_dispatch', which may have overlapping functions.

  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 provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, appropriate contexts, or exclusions. Given sibling tools like 'miyabi__analyze_task_intent' (which might analyze tasks before processing) and 'miyabi__auto_dispatch' (which might handle routing), the lack of differentiation leaves the agent guessing about the optimal use case for this tool.

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

• miyabi__auto_dispatchB
  3.2/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries full burden. It mentions the dispatch behavior but lacks details on how the routing decision is made (e.g., based on criteria, thresholds), what happens if classification fails, whether it's idempotent, or any rate limits/authentication needs. This leaves significant behavioral gaps for a tool that makes routing decisions.

  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 a single, efficient sentence in Japanese that directly states the tool's function and routing logic. It's front-loaded with the core purpose and includes essential context without unnecessary details, making it highly concise and well-structured.

  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?

  Given no annotations, no output schema, and a single parameter with full schema coverage, the description is incomplete. It doesn't explain what the tool returns (e.g., handler identifier, confidence score), error conditions, or behavioral nuances like how 'appropriate' is determined. For a decision-making tool, this lacks critical context.

  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?

  Schema description coverage is 100%, with the single parameter 'prompt' documented as '振り分けるタスクのプロンプト' (prompt of the task to dispatch). The description adds no additional parameter semantics beyond what the schema provides, such as format examples or constraints. With high schema coverage, the baseline score of 3 is appropriate.

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

  Purpose4/5

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

  The description clearly states the tool's purpose: automatically dispatches tasks to appropriate handlers based on task type (development tasks to Miyabi, general tasks to Manus). It uses specific verbs ('振り分けます' - dispatches) and identifies the resource (tasks), but doesn't explicitly differentiate from sibling tools like miyabi__analyze_task_intent or miyabi__handle_development_task.

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

  Usage Guidelines3/5

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

  The description implies usage context by mentioning task types (development vs. general) and target handlers (Miyabi vs. Manus), suggesting this tool is for routing decisions. However, it doesn't provide explicit guidance on when to use this tool versus alternatives like miyabi__handle_development_task or when not to use it (e.g., for tasks already classified).

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