e-Stat MCP

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

With annotations already declaring readOnlyHint=true and destructiveHint=false, the description's safety profile is covered. It adds context about the return fields (name, description, download URL) and intended use, but does not detail pagination, rate limits, or other behavioral nuances. This is adequate given the 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.

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

The description is two concise sentences, front-loaded with the verb and resource, and includes a clear purpose statement. Every word contributes value without redundancy or filler.

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 complex parameter set (14 optional parameters) but with a fully documented schema and an output schema, the description sufficiently covers the tool's role and context. It could mention more about query construction scenarios, but the schema's exhaustive parameter descriptions compensate, making this adequate for an agent to select and invoke.

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 schema description coverage is 100%, and many parameters have rich descriptions including enums and format guidance. The tool description itself does not add parameter details, but the schema already provides comprehensive semantics, so the description adds no extra value beyond what's structured. Baseline of 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 clearly states the tool retrieves catalog information from e-Stat, listing specific content such as statistical names, descriptions, availability, and file download URLs. It also mentions the intended use case (overview grasp and file acquisition), distinguishing it from sibling tools like get-meta-info and get-stats-list.

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 provides clear context on when to use this tool ('統計データの全体像把握やファイル取得用途'), which implies it is for catalog-level exploration rather than detailed metadata or statistics retrieval. However, it does not explicitly exclude cases or mention alternative tools, so it stops short of full guidance.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only safety is covered. The description adds context about the types of metadata returned and how to use the results in subsequent data retrieval, which goes beyond the annotations without contradicting them.

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 two sentences, front-loaded with the primary purpose and followed by a clear workflow note. No redundant or extraneous content.

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 has an output schema and read-only annotations, the compact description is sufficient. It covers the typical usage path (from list to meta to data) and does not need to explain return values because the output schema exists.

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?

Input schema descriptions cover 100% of parameters with detailed explanations (e.g., classId examples, classLimit behavior, lang enum). The description itself does not add parameter-specific information, so the baseline of 3 for full schema coverage 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 clearly states it retrieves meta information (classification items, area, time axis, table presentation) for a stats table ID obtained from e-stat-get-stats-list. It distinguishes from siblings by naming both the source tool (e-stat-get-stats-list) and the downstream consumer (e-stat-get-stats-data), making its role in the workflow explicit.

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 provides workflow context: use after getting a statsDataId from e-stat-get-stats-list and before fetching data with e-stat-get-stats-data. It implies when to use the tool but does not explicitly mention when not to use it or compare it with e-stat-get-data-catalog.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context by stating that the result contains only list and basic information, not actual statistical values ('実際の統計数値は含まれない'), clarifying what the user can expect beyond the annotations.

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

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

The description is two sentences: the first defines the core action, the second clarifies what is excluded and how to proceed for actual data. 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.

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

Given the high parameter count (12), rich schema descriptions, output schema presence, and annotations, the description is complete enough. It adds the crucial note about using an external tool for actual data, which is essential for the overall workflow.

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% for all 12 parameters, including formats, enums, defaults, and semantics. The tool description does not add parameter-level detail beyond mentioning the output includes stats table ID, name, survey year, etc., so it neither improves nor degrades beyond the schema baseline.

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 '指定した条件に基づき、e-Statに登録されている統計表の一覧および基本情報（統計表ID、統計名、調査年月、公開日など）を取得する', which clearly identifies the verb (取得する), the resource (統計表の一覧), and the scope. It also explicitly says actual statistical values are not included, distinguishing it from data-retrieval tools.

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 provides explicit guidance: 'ここで得た統計表IDを e-stat-get-stats-data ツールに渡して取得する', telling users to use the returned IDs with a specific complementary tool for actual data. It lacks comparisons with sibling tools e-stat-get-data-catalog and e-stat-get-meta-info, but the workflow guidance is clear.

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