Server Quality Checklist

Tool Scores

• kaken_get_researcher_grantsA
  3.7/5.0
  Behavior3/5

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

  With no annotations provided, the description must fully disclose behavior. It states that all projects (both PI and co-PI) are returned and hints at available data (e.g., cumulative allocation). However, it omits details on pagination, error handling, output format, or whether the result includes full project details. This is adequate but not thorough.

  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 with three clear sentences: definition, use cases, and comparison with name search. No redundant information. However, it could be slightly more structured (e.g., bullet points for parameters) but overall efficient.

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

  Completeness3/5

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

  Given no output schema, the description should clarify return values. It mentions 'all projects' and implies fields like cumulative allocation, but does not specify the full output structure or pagination. For a simple tool with 3 parameters, it is minimally complete but leaves the agent guessing about the response format.

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

  Parameters2/5

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

  Schema description coverage is low (33%, only researcherNumber described). The description repeats the researcher number format but adds no new meaning for the other parameters (rw, format). Use cases are mentioned but not tied to parameters. The description fails to compensate for the low schema coverage.

  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: retrieve all projects (grants) where a researcher is PI or co-PI using their 8-digit researcher number. It also mentions specific use cases (achievement tracking, time-series analysis, aggregation) and distinguishes itself from sibling tools by noting that name search may mix same-name individuals, reinforcing when this tool is appropriate.

  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 explicit context for use: when you need all projects by a specific researcher and have their number. It warns against using name search due to ambiguity. However, it does not discuss when to use related sibling tools like kaken_get_project or kaken_search_projects, leaving some gaps in guidance.

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

• kaken_get_projectA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description must fully disclose behavior. It implies a read operation but does not explicitly state read-only, authentication needs, error handling for invalid numbers, or any side effects. The mention of equivalence to search adds some context but is insufficient for full transparency.

  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 three sentences, concise and front-loaded. Every sentence adds value, with no redundant information. It efficiently conveys purpose, usage context, and comparison to sibling tools.

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

  Completeness3/5

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

  The description explains the tool's purpose and relation to search, but given the absence of an output schema, it does not describe the return format or fields. With low complexity (2 params), the information is partially complete but omits what the agent can expect after execution.

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

  Parameters2/5

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

  Schema description coverage is 50% (only awardNumber has a description). The tool's description repeats the schema description for awardNumber but adds no details about the format parameter or its enum values. Given low coverage, the description should compensate but fails to explain the second parameter.

  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 action (get details of one project) and the resource (by award number). It distinguishes from sibling tools by noting it's for when the number is already known and explicitly compares to kaken_search_projects.

  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 specifies when to use this tool (when the award number is already known) and provides an alternative (kaken_search_projects with qb), stating that this tool should be prioritized due to clearer purpose.

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

• kaken_search_projectsA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It states the output format (compressed Markdown with specific fields) and mentions that results include project number, representative, affiliation, etc. It implies a read-only search operation. However, it does not disclose potential rate limits, authentication requirements, or pagination behavior beyond the start parameter. The behavioral transparency is good 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 a single paragraph that front-loads the tool's purpose and use cases. It is moderately sized (about 100 characters) and every sentence adds value. It could be slightly more structured (e.g., bullet points for use cases), but it is concise and avoids redundancy.

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

  Completeness3/5

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

  Given 18 parameters and no output schema, the description covers the tool's purpose, use cases, and output format. However, it does not explain pagination details (e.g., how start and rw interact) or mention the output format parameter (format: ai/table/json) beyond the default. The lack of an output schema increases the need for the description to explain return values, but it only briefly mentions the Markdown content. Some completeness gaps exist.

  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 94%, so the baseline is 3. The description adds some value by grouping parameters (e.g., 'フリーワード(kw)・課題名(qa)・分野(qd)・機関(qe)・年度(s1/s2)') and stating they can be combined. However, it does not provide additional semantics beyond what the schema already explains for most parameters. Since coverage is high, the description's contribution is minimal.

  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 searches the KAKEN database for research projects, lists specific use cases (competitor/prior research, trend grasp, reference data collection), and distinguishes itself from sibling tools like kaken_get_project (which retrieves a single project) and kaken_search_researchers (which searches researchers). The verb 'search' combined with the resource 'projects' and the detailed usage scenarios provide high-purpose clarity.

  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 explicitly provides usage scenarios (競合・先行研究調査、特定分野の採択動向把握、申請書作成時の参考データ収集) and mentions combining parameters. However, it does not explicitly state when not to use this tool versus alternatives (e.g., when to use kaken_get_project instead). The context is clear but lacks exclusion criteria.

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

• kaken_search_researchersA
  4/5.0
  Behavior3/5

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

  With no annotations, description must cover behavioral traits. It describes the tool as a search operation returning affiliation, position, and URL, implying read-only behavior. It does not discuss rate limits, authentication, or pagination details (though parameters hint at pagination). Adequate but not rich.

  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?

  Two well-structured sentences. First sentence states purpose and resource, second provides search fields and output. No extraneous information. Front-loaded and efficient.

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

  Completeness4/5

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

  Given 12 parameters, no output schema, and no annotations, the description sufficiently explains the tool's purpose and retrieved fields. It could mention pagination or result limits more explicitly, but the start and rw parameters imply this. Overall complete enough for effective use.

  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 coverage is 75%, so many parameters already have descriptions. The description adds value by grouping search fields (name, number, institution, field) but does not significantly expand on parameter meaning beyond the schema. Baseline 3 is appropriate.

  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 clearly states it searches researchers from KAKEN database, lists retrieved fields (affiliation, position, URL), and specifies use cases (identifying specific researcher or listing by institution/field). This distinguishes it from sibling tools which handle projects or grants.

  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?

  Explicitly describes when to use (identifying specific researcher or listing by institution/field). However, it does not mention when not to use or provide direct comparison with sibling tools, though context is clear.

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