Server Quality Checklist

Tool Scores

• get_stats_data_csvD
  1.9/5.0
  Behavior1/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure but offers nothing beyond the basic purpose. It doesn't mention whether this is a read-only operation, what authentication might be needed, rate limits, pagination behavior (despite 'start_position' and 'limit' parameters), error conditions, or what the CSV output contains. The description is completely inadequate for a tool with 25 parameters.

  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 Japanese sentence that states the core purpose without unnecessary words. It's appropriately sized for what it communicates, though what it communicates is extremely limited. There's no wasted verbiage or structural issues.

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

  Completeness1/5

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

  For a complex tool with 25 parameters (only 1 required), 0% schema description coverage, no annotations, and multiple similar sibling tools, the description is completely inadequate. While an output schema exists (which helps with return values), the description doesn't explain when to use this tool, what the parameters mean, behavioral characteristics, or how it differs from alternatives. This is a data retrieval tool with significant complexity that needs far more explanation.

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

  Parameters1/5

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

  Schema description coverage is 0%, meaning none of the 25 parameters have descriptions in the schema. The tool description provides zero information about any parameters - not even explaining the required 'stats_data_id' or what the various 'cdcat', 'lvcat', 'cdtime', 'cdarea' parameters mean. For a tool with this many undocumented parameters, the description fails completely to add any parameter semantics.

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

  Purpose3/5

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

  The description '統計データをCSVで取得する' (Get statistical data in CSV format) states a clear verb ('取得する' - get) and resource ('統計データ' - statistical data), but it's vague about scope and doesn't distinguish from siblings like 'get_stats_data' or 'get_stats_data_bulk'. It provides basic purpose but lacks specificity about what kind of statistical data or how this differs from similar tools.

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

  Usage Guidelines1/5

  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. With 12 sibling tools including 'get_stats_data' (presumably non-CSV version), 'get_stats_data_bulk', and various catalog/metadata tools, there's no indication of when CSV output is preferred, what prerequisites exist, or when other tools might be more appropriate.

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

• get_data_catalog_csvC
  2.3/5.0
  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 states this is a 'get' operation (implying read-only) and outputs CSV format, but doesn't disclose behavioral traits like whether this is a search/filter tool (given 10 parameters), pagination behavior (start_position, limit), rate limits, authentication requirements, or what 'data catalog information' specifically includes. For a 10-parameter tool with no annotation coverage, this is inadequate.

  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, efficient sentence in Japanese that states the core purpose. It's appropriately concise and front-loaded with the essential action. However, given the tool's complexity (10 parameters), this extreme brevity leaves critical gaps in understanding.

  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 high complexity (10 parameters, 0% schema coverage, no annotations) but with an output schema present (which might describe the CSV structure), the description is incomplete. It doesn't explain the filtering/search capabilities implied by the parameters, the relationship to sibling tools, or behavioral context. The output schema may cover return values, but the description doesn't provide enough context for effective tool selection and use.

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

  Parameters1/5

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

  Schema description coverage is 0% (no parameter descriptions in schema), and the tool has 10 parameters. The description provides zero information about any parameters—not explaining what 'search_word', 'stats_field', 'stats_code', 'gov_code', 'survey_years', 'open_years', 'stats_name_list', 'updated_date', 'start_position', or 'limit' mean or how they affect the CSV output. This fails to compensate for the complete lack of schema documentation.

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

  Purpose3/5

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

  The description 'データカタログ情報をCSVで取得する' (Get data catalog information in CSV) states the basic action (get) and resource (data catalog information) with output format (CSV). However, it doesn't differentiate this tool from its sibling 'get_data_catalog' (which presumably returns non-CSV format) or 'get_meta_info_csv' (which might return metadata in CSV). The purpose is clear but lacks sibling differentiation.

  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 like 'get_data_catalog' (non-CSV format), 'get_stats_list_csv' (statistics list in CSV), or 'get_meta_info_csv' (metadata in CSV). There's no mention of prerequisites, use cases, or exclusions. The agent must infer usage 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.

• get_stats_list_csvC
  2.4/5.0
  Behavior1/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure but provides almost none. It doesn't indicate whether this is a read-only operation, what permissions might be required, whether it has rate limits, what happens with the 10 parameters, or how results are returned. The single sentence only describes the basic function without any operational context.

  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 extremely concise - a single Japanese sentence that directly states the tool's core function. There's no wasted language or unnecessary elaboration. While this conciseness comes at the cost of completeness, the structure is efficient and front-loaded with the essential information.

  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 (10 parameters, no annotations, multiple similar siblings) and the presence of an output schema, the description is insufficient. While the output schema might describe return values, the description doesn't address the tool's behavioral characteristics, parameter meanings, or differentiation from alternatives. For a tool with this many parameters and sibling tools, more context is needed.

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

  Parameters1/5

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

  The description provides zero information about any of the 10 parameters. With 0% schema description coverage and no parameter information in the description, an AI agent would have no semantic understanding of what search_word, survey_years, stats_field, or any other parameters mean or how they should be used. This is particularly problematic given the large number of parameters.

  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: retrieving statistical table information in CSV format. It specifies both the action ('取得する' - get/retrieve) and the resource ('統計表情報' - statistical table information), with the output format ('CSVで') as a key differentiator. However, it doesn't explicitly distinguish this tool from sibling CSV tools like get_data_catalog_csv or get_meta_info_csv.

  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. With multiple CSV-related siblings (get_data_catalog_csv, get_meta_info_csv, get_stats_data_csv) and similar non-CSV tools (get_stats_list), there's no indication of what makes this tool distinct or when it should be preferred over other options. The description is purely functional without contextual guidance.

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

• get_stats_dataC
  2.5/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. It mentions that the tool 'gets' data (implying read-only), but doesn't address authentication requirements, rate limits, error conditions, or what happens when parameters are omitted. The description provides minimal behavioral context beyond the basic operation.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

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

  The description is structured with a brief purpose statement followed by organized parameter documentation. However, the initial purpose statement is overly brief and uninformative. The parameter documentation is comprehensive but could be more efficiently organized, especially for the repetitive lvcat parameters. The structure is adequate but not optimal.

  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 the tool's complexity (25 parameters, no annotations, but has output schema), the description provides good parameter documentation but lacks critical context about usage guidelines, behavioral traits, and differentiation from sibling tools. The presence of an output schema means the description doesn't need to explain return values, but other gaps remain significant for a tool of this complexity.

  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?

  With 0% schema description coverage and 25 parameters, the description provides substantial parameter documentation in Japanese, explaining each parameter's purpose (e.g., '統計表ID', '絞り込み用' for filtering, 'データ取得開始位置', default values). This compensates well for the complete lack of schema descriptions, though some parameters like the lvcat series could use more explanation about their hierarchical relationships.

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

  Purpose2/5

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

  The description states '統計データを取得する' (get statistical data), which is a tautology that essentially restates the tool name 'get_stats_data'. It doesn't specify what kind of statistical data, from what source, or how it differs from sibling tools like 'get_stats_data_bulk' or 'get_stats_data_csv'. The purpose is vague and doesn't provide meaningful differentiation.

  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?

  No guidance is provided about when to use this tool versus alternatives. With multiple sibling tools available (get_stats_data_bulk, get_stats_data_csv, get_stats_list, etc.), the description offers no context about when this specific retrieval method is appropriate versus bulk operations, CSV exports, or other statistical data tools. The agent receives no usage context.

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

• get_meta_info_csvC
  2.6/5.0
  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 retrieves meta information in CSV format, implying a read-only operation, but doesn't specify aspects like whether it requires authentication, has rate limits, what the CSV structure includes, or if it's a one-time fetch versus streaming. For a tool with no annotation coverage, this leaves significant behavioral gaps.

  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, concise sentence in Japanese that directly states the tool's function. It's front-loaded with the core purpose and wastes no words. However, the brevity comes at the cost of completeness, as it omits necessary details for effective use.

  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 the tool has an output schema (which likely defines the CSV structure), the description doesn't need to explain return values. However, with no annotations, one parameter of unclear semantics, and multiple sibling tools, the description is minimally adequate but lacks guidance on usage, parameter meaning, and behavioral context. It meets a basic threshold but has clear gaps.

  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?

  The input schema has one parameter 'stats_data_id' with 0% description coverage, meaning its meaning is undocumented. The tool description adds no information about this parameter—it doesn't explain what 'stats_data_id' represents, how to obtain it, or its format. With low schema coverage, the description fails to compensate, leaving the parameter's semantics unclear.

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

  Purpose3/5

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

  The description states the tool's purpose in Japanese as 'get meta information of statistical tables in CSV format.' This is clear about the verb (get) and resource (meta information of statistical tables), but it doesn't differentiate from sibling tools like 'get_meta_info' (which likely returns non-CSV format) or 'get_stats_data_csv' (which might return actual data, not metadata). The purpose is understandable but lacks sibling distinction.

  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 when to choose CSV format over other formats (e.g., from 'get_meta_info'), what context it's suited for, or any prerequisites. Without such information, users must infer usage from the name and sibling tools alone.

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

• get_data_catalogC
  2.8/5.0
  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 for behavioral disclosure. It only states the tool 'gets' information without describing whether this is a read-only operation, how results are returned (format, pagination), error conditions, or any rate limits. For a tool with 10 parameters and no annotation coverage, this is insufficient behavioral context.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

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

  The description is appropriately brief with a single sentence purpose statement followed by parameter and return sections. However, the structure could be more front-loaded with critical usage information, and the Japanese/English mix may create clarity issues for some agents.

  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 the tool's complexity (10 parameters, no annotations) and the presence of an output schema, the description provides basic purpose and parameter semantics but lacks critical context about when to use it versus siblings, behavioral characteristics, and parameter interactions. The output schema reduces the need to describe return values, but significant gaps remain.

  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?

  With 0% schema description coverage, the description compensates by listing all 10 parameters with Japanese labels that provide semantic meaning (e.g., 'search_word: search keyword', 'stats_field: statistical field code'). This adds significant value beyond the bare schema, though it doesn't explain parameter interactions, format requirements, or default behaviors.

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

  Purpose3/5

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

  The description states the tool 'gets data catalog information' in Japanese, which translates to a clear verb ('get') and resource ('data catalog information'). However, it doesn't distinguish this tool from its many siblings (like get_data_catalog_csv, get_stats_list, search_stats_by_keyword), leaving the specific scope and differentiation unclear.

  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?

  No guidance is provided on when to use this tool versus alternatives. With 12 sibling tools including other catalog-related tools (get_data_catalog_csv) and search tools (search_stats_by_keyword), the description offers no context about appropriate use cases, prerequisites, or comparisons to similar tools.

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

• get_datasetC
  2.8/5.0
  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 that dataset_id is optional (for listing available datasets) and describes pagination with start_position and limit, which adds some behavioral context. However, it lacks critical details like authentication requirements, rate limits, error conditions, or whether this is a read-only operation (implied but not stated).

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

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

  The description is reasonably concise with a purpose statement followed by parameter and return sections. However, the structure mixes Japanese and English inconsistently, and the purpose statement is overly brief. Some sentences could be more informative without adding bulk.

  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 annotations and an output schema (implied by 'Returns'), the description covers basic purpose and parameters adequately. However, for a data retrieval tool with many siblings, it lacks sufficient context about what 'データセット情報' includes versus other tools' outputs, making completeness marginal.

  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?

  With 0% schema description coverage, the description compensates by explaining all three parameters: dataset_id (optional, for listing when omitted), start_position (data retrieval start position), and limit (number of items to retrieve). This adds meaningful semantics beyond the bare schema, though it could specify data types or constraints more clearly.

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

  Purpose3/5

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

  The description states 'データセットを参照する' (refer to/view a dataset), which provides a basic verb+resource but is vague about scope and functionality. It doesn't clearly distinguish this tool from sibling tools like 'get_data_catalog' or 'get_meta_info', leaving ambiguity about what specifically this tool retrieves versus others.

  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?

  No guidance is provided on when to use this tool versus alternatives. With multiple sibling tools for data retrieval (e.g., get_data_catalog, get_meta_info, get_stats_data), the description offers no context on appropriate use cases, prerequisites, or exclusions, leaving the agent to guess based on tool names alone.

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

• get_meta_infoC
  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 full burden. While it states this is a retrieval operation ('gets'), it doesn't disclose important behavioral traits like whether this requires authentication, has rate limits, what happens with invalid IDs, or the structure of the returned metadata beyond mentioning 'classification items, time axes, etc.'

  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 appropriately concise with a clear main statement followed by Args and Returns sections. The bilingual format (Japanese main text with English section headers) is slightly unconventional but doesn't significantly impact clarity. Every sentence serves a purpose.

  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 the tool has an output schema (which handles return value documentation) and only one parameter, the description is minimally adequate. However, for a metadata retrieval tool in a rich statistical data context with many sibling tools, it should provide more guidance about when this specific metadata format is needed versus CSV alternatives.

  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?

  With 0% schema description coverage and only 1 parameter, the description provides the essential semantic meaning: 'stats_data_id' is a 'statistical table ID'. This adequately compensates for the lack of schema documentation for this single required parameter.

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

  Purpose3/5

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

  The description states the tool 'gets metadata for statistical tables' which is a clear verb+resource combination. However, it doesn't distinguish this from sibling tools like 'get_meta_info_csv' or explain what makes this metadata retrieval different from other data retrieval tools in the set.

  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?

  No guidance is provided about when to use this tool versus alternatives. With siblings like 'get_meta_info_csv' and 'get_stats_data' available, the description offers no context about when this specific metadata retrieval is appropriate versus getting the actual data or CSV-formatted metadata.

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

• get_stats_data_bulkC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden but offers minimal behavioral information. It mentions bulk retrieval but doesn't disclose rate limits, authentication requirements, error handling for invalid IDs, whether the operation is read-only or has side effects, or what happens when both 'stats_data_ids' and 'dataset_ids' are provided. For a bulk operation with 4 parameters, this is insufficient 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 a single, efficient Japanese sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized for a bulk retrieval operation and front-loads the core functionality. Every word earns its place.

  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 the tool has an output schema (which handles return values), 4 parameters with 0% schema coverage, and no annotations, the description is minimally complete. It identifies the resource and bulk nature but lacks crucial context about parameter usage, behavioral constraints, and differentiation from siblings. For a bulk data retrieval tool in a statistical system, this leaves significant gaps for the agent.

  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 0%, so the description must compensate but fails to do so. It mentions '複数の統計表ID/データセットID' (multiple statistical table IDs/dataset IDs) which maps to 'stats_data_ids' and 'dataset_ids' parameters, but doesn't explain the relationship between these two ID types, what 'start_position' and 'limit' control (likely pagination), or format requirements for IDs. With 4 undocumented parameters, this is a significant gap.

  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 verb ('一括取得する' - bulk retrieve) and resource ('統計データ' - statistical data) with the scope of multiple IDs. It distinguishes from single-ID retrieval tools like 'get_stats_data' by specifying bulk operation. However, it doesn't explicitly differentiate from all sibling tools like 'get_stats_data_csv' which might also retrieve bulk data in CSV format.

  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 when to use bulk retrieval versus single retrieval ('get_stats_data'), when to use this versus CSV export tools ('get_stats_data_csv'), or any prerequisites or constraints for bulk operations. The agent must infer usage from the name and description alone.

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

• post_datasetC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It states this is a registration (write) operation and mentions a return value ('登録結果'), but lacks critical details: authentication requirements, whether registration is idempotent or reversible, rate limits, error conditions, or what the return result contains. For a mutation tool with zero annotation coverage, this is a significant gap.

  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 appropriately sized and front-loaded with the core purpose first. The Args/Returns sections are structured clearly, though the Japanese text might require translation for some agents. Every sentence earns its place, with no redundant information.

  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 the tool's complexity (4 parameters, mutation operation) and the presence of an output schema (which handles return values), the description is moderately complete. It covers the basic purpose and parameters but lacks behavioral context (e.g., side effects, permissions) and detailed usage guidelines. With no annotations and incomplete parameter documentation, it's adequate but has clear gaps.

  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 0%, so the description must compensate. It lists all 4 parameters with brief explanations (e.g., '統計表ID' for stats_data_id, '取得条件' for conditions), adding basic semantic meaning beyond the schema's type definitions. However, it doesn't provide format examples, constraints, or usage details (e.g., what cdCatXX, cdTime, cdArea mean in conditions), leaving parameters partially documented.

  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 as 'データセットを登録する' (register a dataset), which is a specific verb+resource combination. It distinguishes itself from sibling tools that are primarily get/search operations (e.g., get_dataset, get_stats_data, search_stats_by_keyword), though it doesn't explicitly name alternatives for dataset registration.

  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, constraints, or relationships with sibling tools (e.g., whether you need to use get_stats_data first to obtain stats_data_id). Usage is implied only by the tool's name and purpose.

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

• search_stats_by_keywordB
  3.1/5.0
  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 it's a 'helper tool' and describes the return as a 'list of search results,' but lacks critical behavioral details: no information on permissions, rate limits, error handling, pagination, or what 'search' entails (e.g., fuzzy matching, exact matches). This is a significant gap for a search tool with no annotation coverage.

  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 appropriately sized and front-loaded: the first sentence states the purpose, followed by a helper tool note, then parameter and return sections. Each sentence adds value, though the structure could be slightly more streamlined (e.g., integrating the helper note into the purpose).

  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 2 parameters with 0% schema coverage, no annotations, and an output schema present, the description is moderately complete. It covers parameter semantics well and notes the return type, but lacks behavioral context (e.g., search scope, result format details). The output schema reduces the need to explain returns, but more guidance on tool behavior would improve completeness.

  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 description coverage is 0%, so the description must compensate. It adds meaningful semantics: 'keyword' is explained with examples ('population,' 'GDP,' 'employment'), and 'limit' is clarified as 'number of items to retrieve (default 20 items).' This goes beyond the bare schema, though it doesn't detail constraints like keyword length or limit ranges.

  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: 'search statistical information by keyword' and identifies it as a 'helper tool for easily searching statistical tables.' It specifies the verb ('search') and resource ('statistical information'), though it doesn't explicitly differentiate from sibling tools like 'get_stats_list' or 'get_stats_data' beyond being a 'helper tool.'

  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 mentions it's a 'helper tool for easily searching statistical tables' but doesn't specify scenarios, prerequisites, or exclusions compared to siblings like 'get_stats_list' or 'get_stats_data,' leaving usage context implied at best.

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

• get_stats_fieldsB
  3.3/5.0
  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. The description only states what the tool returns, without mentioning any behavioral traits such as whether this is a read-only operation, potential rate limits, authentication requirements, or what format the output takes. While the existence of an output schema helps, the description itself lacks behavioral context.

  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 extremely concise - a single Japanese sentence that directly states the tool's purpose with no wasted words. It's appropriately sized for a simple retrieval tool with no parameters and gets straight to the point without unnecessary elaboration.

  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 that this is a simple retrieval tool with zero parameters and an output schema exists, the description is reasonably complete for its purpose. The output schema will handle documenting return values, so the description only needs to state what the tool does. However, it could benefit from clarifying how this differs from similar sibling tools in the context of the overall API.

  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 tool has zero parameters, and schema description coverage is 100% (though there are no parameters to describe). The description doesn't need to compensate for any parameter documentation gaps. A baseline of 4 is appropriate for a parameterless tool where the schema fully covers the input structure (which is empty).

  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: '統計分野コード一覧を返す' (returns a list of statistical field codes). It uses a specific verb ('返す' - returns) and resource ('統計分野コード一覧' - statistical field code list). However, it doesn't explicitly differentiate from sibling tools like 'get_stats_list' or 'get_meta_info', which might also return lists of statistical information.

  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. With multiple sibling tools that appear to retrieve statistical data (e.g., 'get_stats_list', 'get_meta_info', 'get_stats_data'), there's no indication of what distinguishes this tool's functionality or when it should be preferred over other list-retrieval tools.

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

• get_stats_listB
  3.4/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. While it mentions the tool searches for statistical table information and describes parameters, it doesn't disclose important behavioral traits like whether this is a read-only operation, potential rate limits, authentication requirements, pagination behavior (beyond start_position and limit parameters), or what happens when no results match. The description is functional but lacks behavioral context.

  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 (purpose, Args, Returns) and efficiently organized. Each parameter explanation is concise yet informative. The only minor inefficiency is the Japanese-to-English transition in parameter names, but this doesn't significantly impact usability. Every sentence earns its place.

  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 the complexity (10 parameters, 0% schema coverage, no annotations) and the presence of an output schema, the description is reasonably complete. It thoroughly documents all parameters and their semantics, which is crucial given the poor schema coverage. The output schema handles return value documentation, so the description appropriately focuses on input parameters and tool purpose. The main gap is lack of behavioral context and usage guidelines.

  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?

  With 0% schema description coverage and 10 parameters, the description provides excellent parameter semantics. It clearly explains each parameter's purpose, format requirements (YYYY for years, YYYY-YYYY for ranges, 2-digit codes, 5/8-digit codes), defaults (limit defaults to 10), and constraints (maximum 100 for limit). This fully compensates for the lack of schema descriptions and adds substantial value beyond the bare schema.

  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 '統計表情報を検索する' (search for statistical table information), which is a specific verb+resource combination. It distinguishes this tool from siblings like get_stats_data (which retrieves actual data) and get_stats_fields (which gets field information). However, it doesn't explicitly differentiate from search_stats_by_keyword, which appears to serve a similar search function.

  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. With multiple sibling tools like get_stats_list_csv, get_data_catalog, and search_stats_by_keyword, there's no indication of when this specific search/list tool is preferred over others. The description only states what the tool does, not when to use it.

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