Same-job hourly wages in Japan, US, UK, Germany, France; ranks of 31 business risks, Japan vs US.
Scored across 6 tools
The three wage tools (compare_wages, wages_ranking, france_groups) are separated by scope — cross-country ratio comparison, single-country ranking, and the France/Insee grouping — and the descriptions make that clear. risk_categories and risk_overview are also distinguishable (category ranking vs. aggregate summary), though a first-time agent could momentarily hesitate between the wage tools.
All names are lowercase snake_case, which is good, but the conventions are mixed: verb_noun (compare_wages), noun_noun (risk_categories, wages_ranking, france_groups), and a prefix-style about_data. Readable, but no predictable pattern an agent can rely on to guess a name.
Six tools is well within a healthy range for a read-only data explorer covering two datasets (wages and business risks). Each tool maps to a distinct slice of the data, though the surface is on the lean side and relies on parameters (query, sort_by, field) for depth.
The domain is covered end to end for exploration: metadata (about_data), cross-country and within-country wage views, a France-specific view, plus risk category rankings and a risk overview. Minor gaps — no per-company risk lookup or drill-down, and no UK/Germany/Japan standalone ranking beyond the generic wages_ranking — but nothing blocks core workflows.
このデータの範囲と、二つの読みもののページ。
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full behavioral burden. It implies an informational read but never explicitly states that it is non-destructive, what it returns, or whether it has side effects; it only hints at subject matter.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence with no filler and no redundant clauses. Its brevity is efficient, though it borders on being too cryptic to be useful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter tool with no output schema or annotations, the description is only minimally adequate: it names the data scope and two reading pages but does not clarify what "two readings" refers to or what the returned result looks like. It provides a high-level hint but leaves meaningful gaps for an agent deciding whether to call it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so there are no parameter semantics to document and the baseline 4 applies. The description does not need to compensate for any parameter schema gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description identifies the resource as "this data" and says it covers its scope plus two reading pages, which gives a rough idea of the tool's content. However, it is phrased as a noun fragment without a clear action verb, and it does not distinguish this tool from siblings such as risk_overview or france_groups.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives no when-to-use or when-not-to-use guidance, no alternatives, and no prerequisites. An agent must infer that this is a metadata/about tool from the name and vague content alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
同じ仕事の時給を、日本・米国・英国・ドイツで比べる（56 の仕事）。円に直さず、その国の仕事全体の平均の時給の何倍か（ratio）で返す。query は日本語の仕事の名前か、英語の職業名（例：薬剤師・保育士・software・nurse）。field で分野だけに絞れる。どちらも省くと仕事の一覧。
| Name | Required | Description | Default |
|---|---|---|---|
| field | No | 分野（医療／介護・保育・教育／技術・専門／事務・販売／サービス／運転・運輸／建設・ものづくり）。一部だけでもよい | |
| query | No | 仕事の名前（日本語）か職業名（英語）の一部 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and does disclose the non-obvious behavior that results are returned as a ratio to the country-wide average wage with no yen conversion, plus the default listing behavior when parameters are omitted. It does not discuss permissions, limits, or the shape of the returned values beyond the ratio concept.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four short sentences, front-loaded with the core comparison and the ratio semantics, then parameters, then the no-parameter case. No filler or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, so explaining the ratio return value is essential and is done clearly; parameter behavior and the default listing are also covered. Only the concrete shape of the response stays implicit, which is a minor gap for a two-parameter read tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already explains both parameters; the description nevertheless adds examples (薬剤師・保育士・software・nurse) and clarifies that query matches a partial name, and explains the both-omitted case, which is genuinely beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The opening sentence names a specific verb (compare), resource (hourly wages), scope (Japan/US/UK/Germany, 56 jobs), and distinguishes it from the sibling wages_ranking by stating that results are relative ratios rather than currency conversions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It states the accepted forms for query (Japanese job names or English occupation names, with examples), that field narrows by category, and that omitting both returns the full job list. It does not explicitly say when to prefer a sibling such as wages_ranking over this tool, so it falls short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
フランス（Insee の職業の大くくり 9 区分）と、日本でそれに当たる職業をまとめた時給の倍率の比べ。
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It implies a read-only statistical lookup, but says nothing about the shape of the result, whether it is aggregated or per-category, or what the '比率' baseline is. Only the data source (Insee 9 categories) is disclosed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single short sentence with no filler, and the data source is front-loaded. Its brevity is close to under-specification rather than padding, but nothing is wasted.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter lookup this covers the data source and the comparison concept, which is the minimum an agent needs. Without an output schema, though, it should say more about what the ratios look like and how the result differs from compare_wages.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, so there is nothing for the description to compensate for; baseline 4 applies. The mention of the fixed 9 Insee categories usefully explains why no filtering input exists.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names the resource (French Insee 9 occupational categories mapped to Japanese equivalents) and the operation (comparing hourly-wage multipliers), so an agent can roughly tell what it returns. However the phrasing is grammatically garbled ('の比べ') and it never distinguishes itself from the sibling compare_wages, which sounds like it does the same comparison.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no indication of when to prefer this over compare_wages or wages_ranking, nor any prerequisites or exclusions. The agent must infer usage purely from the data-source mention.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
日本 3,766 社と米国 3,808 社の上場企業が「事業のリスク」の見出しに書いた心配ごとの 31 の種類。日米の順位・割合・順位の差。query で種類の名前を絞れる。sort_by は JP（日本の順位）・US（米国の順位）・gap（順位の差が大きい順）。
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | 種類の名前の一部（例：人手・災害・株主・AI・金利） | |
| sort_by | No | 並べ方（省くと JP） |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the behavioral burden. It discloses useful dataset context such as sample sizes and the metrics returned, but it does not describe return format, pagination, or other operational traits an agent might need.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and front-loaded, stating the dataset scope first, then filtering and sorting behavior. Every sentence contributes useful information without repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-parameter read-only data exploration tool with no annotations or output schema, the description supplies enough context about the dataset, metrics, filtering, and sorting to select and call it correctly. The main missing piece is explicit differentiation from the sibling risk_overview tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description still adds meaningful semantics: query filters by part of a category name, and sort_by values are explained as JP rank, US rank, and largest rank gap. This goes beyond simply repeating enum labels.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the resource: 31 categories of business risks reported by 3,766 Japanese and 3,808 US listed companies, including Japan/US rankings, proportions, and rank gaps. It is specific about scope and metrics, but it does not explicitly distinguish this tool from the sibling risk_overview tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by explaining that query can narrow categories by name and sort_by controls ordering. However, it does not state when to use this tool instead of alternatives such as risk_overview, nor does it provide exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
日米の事業のリスクのまとめ：社数・1 社あたりの見出しの数・米国で AI・生成 AI・関税・Google と書いた会社の数と割合・米国の業種ごとの AI と Google の割合・小売の会社の 8 つの軸（日米）。
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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 lists what data is summarized but does not state whether the operation is read-only, where the data comes from, how fresh it is, or what the response looks like.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that states the purpose first and then enumerates the included metrics. It is dense but every listed item appears to earn its place as content specification.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a no-parameter reporting tool with no annotations and no output schema, the description sufficiently lists what the overview includes. However, it does not explain the output format, data freshness, or how to interpret items like the retail 8 axes, leaving clear gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, which establishes a baseline of 4 under the rubric. No parameter semantics are needed, and the description does not introduce any parameter-related ambiguity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific resource, a Japan/US business risk summary, and enumerates concrete metrics such as company counts, headline counts, AI/generative AI/tariff/Google mentions, industry breakdowns, and retail axes. It does not differentiate the tool from sibling risk_categories, so it 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.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool instead of siblings like risk_categories or about_data, and no exclusions or prerequisites are stated. The description only lists contents, leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
一つの国の中で、仕事全体の平均に対する倍率（ratio）の高い順か低い順に並べる。
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | 何件まで（省くと 10） | |
| order | No | 高い順（high・省くとこちら）か低い順（low） | |
| country | Yes | 国（JP 日本・US 米国・UK 英国・DE ドイツ） |
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 does not state whether the operation is read-only, whether it has side effects, what permissions are required, or any rate limits. The only behavioral hint is that it returns a sorted list, but that is implied rather than explicitly stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. It efficiently conveys the core operation without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (three parameters, no output schema), the description covers the basic purpose but omits important context such as the return format (e.g., what fields are included in the ranking) and any behavioral characteristics. Without an output schema, the description should ideally explain what the agent can expect in the response. It is adequate but with clear gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the parameters are fully documented in the schema. The description adds minor conceptual context (ratio to overall average, within one country) but does not provide syntax or format details beyond what the schema already offers. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific operation (sorting jobs by ratio to the overall average within one country) and clarifies the ranking direction. It does not explicitly distinguish itself from siblings like compare_wages, but the scope (within a single country, ratio-based ranking) is clear enough for an agent to understand its unique purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus alternatives such as compare_wages. The description only explains what the tool does, leaving the agent to infer appropriate usage contexts. No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
about_datacompare_wagesfrance_groupsrisk_categoriesrisk_overviewwages_rankingJapan minimum wage by prefecture, 協会けんぽ rates, pensions, benefits, holidays, tax figures, sourced.
Japan payroll & social insurance. 日本の給与計算・社会保険。47都道府県の料率、源泉所得税、割増賃金、有給、標準報酬月額の改定、最低賃金。根拠の条文つき。
Food additive regulations of Japan, the EU and the US, side by side, with sources (free tier).
Public construction cost data for Japan and the U.S., each row with its source URL and licence.
Add one secure layer between your agents and this server.