agri-ja 日本の農業政策・補助金・米の概算金

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

The description discloses that results are candidates with typical estimates, not guaranteed figures, and that actual requirements need official confirmation. It also adds a minimum input constraint, which goes beyond the readOnlyHint annotation. No contradictions with 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 front-loaded with the core purpose, then systematically explains each parameter and its enum values with clear separators. Though long, every sentence is informative and necessary given the 21 total enum values.

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?

The tool has three enum parameters and no output schema; the description covers all input possibilities and even hints at return contents (amounts/subsidy rates) while adding caveats about verification. It could be more explicit about the exact return format, but is otherwise sufficient.

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 only provides short labels (品目, やりたいこと, 立場), while the description fully explains each enum value with Japanese translations and context (e.g., 'new-farmer' means starting soon or recently, 'machine' means buying/renewing machinery). This significantly enriches 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 description clearly states that the tool returns candidate subsidies/grants/funds in Japanese agriculture based on audience, purpose, and crop, using a specific verb ('返す') and resource. However, it does not explicitly differentiate itself from sibling tools like search_articles or rice_advance_payment.

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 provides clear usage guidance: specify any of the three parameters with at least one required, and notes that amounts are estimates requiring verification. However, it does not mention when to prefer this tool over siblings.

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?

Beyond the readOnlyHint annotation, the description discloses that the tool does not return the full article text and that the return value includes a URL for readers needing details. This is important behavioral context not present in 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, front-loaded with the return items, and the second sentence adds the crucial limitation and follow-up action. No waste.

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 simple read-only tool with one parameter, the description covers what is returned, what is not returned, and how to access the full article. Minor ambiguity between the article URL and primary-source URL, but overall complete.

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 already fully documents the 'slug' parameter with format examples and the option to pass a full URL. The description adds no additional parameter semantics, so the baseline of 3 applies given high schema coverage.

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 returns key points (takeaways), heading structure, opening excerpt, primary source URL, and update date for a single agri-ja.net article. It uses a specific verb (返す) and resource, distinguishing it from sibling search 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 no guidance on when to use this tool versus sibling tools like search_articles. It only notes that the full text is not returned and suggests guiding readers to the URL, which is a behavioral note, not a tool-selection guideline.

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 the description adds valuable context: the data is independently compiled by agri-ja.net from JA and press releases, amounts are per 60kg, and the response includes comparison and unannounced status. No contradictions with 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 four sentences, each providing distinct information: main function, included fields, data source, and unit. It is front-loaded and contains 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?

For a relatively simple read-only tool with optional filters and no output schema, the description adequately covers the return content and data source. It could mention default behavior with no filters, but the provided details are sufficient for effective use.

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?

All three parameters (brand, prefecture, onlyAnnounced) are fully documented in the input schema with descriptions. The tool description adds no additional parameter-specific semantics, so the baseline of 3 applies.

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 returns advance payment amounts for 2026 rice by JA/prefecture, including year-over-year comparison, announcement date, and unannounced status. This specific verb+resource clearly distinguishes it from sibling tools like find_subsidy and article search 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 implies this is the primary tool for this data by noting that few cross-sectional lists exist, but it does not explicitly provide when-to-use or when-not-to-use guidance relative to alternatives. It provides clear context but lacks explicit exclusions.

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 indicate read-only behavior, but the description adds valuable behavioral details: space-separated keywords act as AND filters, and the return value includes article URLs for citation. This goes beyond what the annotations provide, though it stops short of explaining other response characteristics.

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 concise, two sentences plus a citation instruction, all information is relevant. It is front-loaded with the action ('search') and resource ('articles'), and each sentence earns its place without fluff.

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 simple search tool, the description covers the content scope, keyword semantics, and return value usage. It omits explicit guidance on when not to use it, but the tool is straightforward and the annotations plus schema cover the remaining operational aspects.

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%, so the baseline is 3. The description enhances understanding by explaining the AND semantics of the query parameter, which is not explicit in the schema's example. This adds meaningful semantic context 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 description clearly states the tool searches explanatory articles on agri-ja.net by keyword, and specifies the content domain (Japanese agricultural policy, subsidies, grants, etc.). It distinguishes itself from siblings by focusing on article search rather than subsidy lookup or article retrieval.

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 when to use the tool (to find articles on agricultural policy topics) and provides a citation instruction, but it does not explicitly mention alternatives or exclusion cases. Usage context is clear but no sibling differentiation is stated.

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