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

The description discloses that the tool performs static analysis and does not use screenshots, which is a meaningful behavioral trait. It also lists the specific checks it performs. However, with no annotations provided, the description carries the full burden; it doesn't disclose whether the tool modifies anything (it appears read-only), what the output format is, or whether it can handle both URL and code simultaneously. The static-analysis disclosure is useful but incomplete.

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: two sentences. The first sentence states the action and resource, the second lists the specific checks and the exclusion of screenshots. It is front-loaded with the core purpose. Minor inefficiency: the list of checks could be seen as detail, but it's valuable for an agent deciding whether to invoke this tool.

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 single-parameter tool with no output schema, the description is reasonably complete: it tells the agent what input to provide and what the tool will check. However, it doesn't describe the output format (e.g., a list of issues, severity levels), which an agent might need to interpret the result. It also doesn't state whether the tool is read-only or if it requires network access for URLs. Given the tool's moderate complexity, a bit more context would be helpful.

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 documents the single parameter 'url_or_code' as '点検したいURLまたはJSX/HTML'. The description adds the context that the tool accepts either a URL or code, which aligns with the parameter name. However, it doesn't add details like whether the code must be JSX/HTML specifically or whether a URL must be publicly accessible. Baseline 3 is appropriate since the schema covers the parameter fully.

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 verb ('点検します' = inspects/reviews) and a clear resource (URL string or code), and lists the specific issues it checks for (English navigation, Inter font, small text, missing furigana, missing legal links). This distinguishes it from siblings like get_jp_rules or get_jp_copy_patterns, which are retrieval tools, though it doesn't explicitly name a sibling alternative.

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 it: when you have a URL or code and need a static review against Japanese UI requirements. It also states what it does NOT use ('スクリーンショットは使いません'), which is a useful exclusion. However, it doesn't explicitly contrast with sibling tools like get_jp_rules or recommend_jp, nor does it state when to prefer those alternatives.

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?

No annotations are provided, so the description carries the full burden. It discloses that providing a slug augments the response with structural notes (color ratios, margins, IA), but it does not describe return format, behavior for missing/invalid slugs, or any side-effect/permission context.

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 compact sentences with no filler. The main action is front-loaded, and the conditional slug behavior is presented immediately after.

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 one-optional-parameter getter, the description gives enough high-level context about default behavior and conditional output, even without an output schema. It stops short of specifying exact return structure or edge cases, but the tool is simple enough that these are minor 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 coverage for the single slug parameter is 100%, but the description adds meaningful semantics beyond the schema: it explains that supplying the slug attaches site structure notes and enumerates what those notes cover. This justifies a score above the 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 a specific action and resource: returning the default Japan-oriented design system, with optional slug-based structural notes. This is clear, though it does not explicitly differentiate itself from siblings like get_jp_rules or get_reference_jsx.

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, and no exclusions or prerequisites are stated. The only conditional information is about the optional slug parameter, which concerns invocation behavior rather than tool selection.

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?

With no annotations, the description carries the full burden and does add one meaningful behavioral trait: outputs are original examples, not re-used wording from reference sites, which sets provenance expectations. However, it does not explicitly state read-only/side-effect-free behavior or describe how copies are generated or selected, leaving the safety profile to be inferred from the verb '返します.'

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?

Exactly two short sentences with zero filler: the first states the action and scope, the second adds the provenance caveat that prevents confusion with site-scraping tools. Information is efficiently front-loaded.

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 single-parameter lookup tool with a fully documented enum and no output schema, the description is nearly sufficient: it states the categories and the origin of the examples. The only gap is that the return format (e.g., array of strings vs. structured objects) is not described, though it is largely inferable for a copy-example catalog.

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% (page_type is documented as 'ページ要素の種類' with a full enum), so the baseline of 3 applies. The description merely echoes the schema's enum values (hero, cta, form, error, nav, footer) without adding format, case, or value-usage details, adding no meaning 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 states a specific verb ('返します' / returns) and a clear resource (日本語コピー例, Japanese copy examples), scoped to six enumerated page-element categories that exactly mirror the input enum. The clarifying clause 'オリジナル例であり、参照サイトの文言ではありません' actively distinguishes this tool from reference-site siblings (search_jp_sites, get_reference_jsx) by asserting the output is original, not site-sourced text.

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?

Usage context is implied but not stated: the enumerated page types tell an agent which requests fit, and the originality clause implies this tool is for original copy rather than verbatim site text. However, there is no explicit when-to-use or when-not-to-use guidance, and no sibling is named as an alternative for legal blocks (get_jp_legal_blocks) or form specs (get_jp_form_spec).

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?

No annotations are provided, so the description bears the full burden of behavioral disclosure. It discloses the returned content (the enumerated fields), which is genuinely useful, but it says nothing about response format, error behavior, or any side effects. As a read-only getter this is acceptable but thin; there is no contradiction with annotations since none exist.

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 front-loaded sentence states the purpose first, followed by the field enumeration. There is no filler or redundancy, and every word contributes. It is appropriately compact for a simple retrieval tool, though slightly more structure (e.g., a separate note on output format) would not have hurt.

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 parameterless getter with no output schema, the description is reasonably complete: it tells the agent exactly what fields the spec contains. However, it omits the shape of the response (object keys, nesting, or format) and does not clarify what 'ご用件' maps to, leaving mild ambiguity about what an agent should expect as a return value.

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 and the schema is empty, so the description correctly carries no parameter documentation burden. The baseline for zero-parameter tools is 4, and the description appropriately focuses on describing the return content rather than parameters. Nothing is missing here.

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 verb-resource pair ('日本語フォーム仕様を返します' — returns the Japanese form spec) and enumerates the form fields (姓・名・フリガナ・email・tel・郵便番号・都道府県・住所・ご用件). This is clear enough to distinguish it from sibling tools like get_jp_copy_patterns or get_jp_legal_blocks, which target different resources, though it never names a sibling explicitly.

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 the nine siblings (get_jp_copy_patterns, get_design_system, recommend_jp, etc.). The field list implies a contact/input-form use case, but the description never states a trigger condition, an alternative, or a when-not-to-use case. With so many siblings, explicit routing would materially help.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds useful context by noting that EC includes specific legal items, but it does not describe the output format, error behavior, or any side effects. For a simple get operation, this is adequate but not comprehensive.

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 core purpose and then a specific detail. Every word is informative, with no redundant or filler 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?

The tool is simple with one parameter and no output schema, but the description omits any indication of the return value format (e.g., array, string, object). An agent would not know what to expect from the call, which is a significant gap given there is no output schema to fall back on.

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% as the enum values are fully listed in the parameter description. The tool description mentions EC, which corresponds to one enum value, but it does not add meaning to the other site types or provide additional context 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.

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

The description clearly states the tool returns required notations (必須表記) for each site type, and adds specific detail about EC including legal disclosure items under the Act on Specified Commercial Transactions. This makes the purpose specific and distinguishable from sibling tools like get_jp_copy_patterns or get_jp_form_spec, which focus on other aspects.

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 explicit guidance on when to use this tool versus alternatives. It does not mention any conditions, exclusions, or references to other tools, leaving the agent to infer usage from the name and purpose alone.

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?

No annotations are provided, so the description carries full responsibility for behavioral disclosure. It only states the tool 'returns' rules, with no information about output format, structure, size, or any limitations. This is a minimal read operation but lacks any behavioral detail beyond its basic function.

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 sentence, front-loaded with the primary action and resource, followed by a compact list of content categories. There is no waste, and the structure is easy to scan.

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 description lists the rule categories returned, which helps an agent understand scope. However, it does not describe the output format (e.g., structured JSON, text) and does not differentiate from sibling get_jp_* tools beyond the category list. Given there is no output schema, more detail on the response would improve completeness.

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 the schema already trivially covers everything. The description adds nothing parameter-related, but per the rubric the baseline for 0 params is 4. It is not penalized for missing param info that cannot exist.

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 the tool returns Japanese UI rules and enumerates specific categories (dates, prices, CTA, body size, tap, forms, color meanings, typography). This gives a clear verb-resource pairing and differentiates it from siblings like get_jp_copy_patterns or get_jp_form_spec by content domain, though it does not explicitly name alternatives.

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?

Usage is implied: the tool is for fetching Japanese UI rules. However, there is no explicit guidance on when to prefer this over siblings like get_jp_legal_blocks or get_jp_form_spec, nor any exclusions. Given the list of siblings, explicit routing would improve the score.

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?

No annotations are provided, so the description bears the full behavioral disclosure burden. It does disclose a key trait: the returned JSX is a reference, not actual site markup, which prevents misinterpretation. However, it does not state whether the operation is read-only, what happens if the id is invalid, or whether any authentication is required. For a simple getter, the disclosure of the 'reference-only' nature adds value, but it leaves other aspects unaddressed.

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, concise sentence that delivers the core function and a clarifying note. There is no filler, and the most important information (returns JSX by id) is front-loaded. Every word earns its place, making this an exemplary concise description.

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 one-parameter retrieval tool with no output schema, the description is largely sufficient: it states the resource and the key differentiator (reference vs. actual markup). It does not mention potential error conditions or return format, but given the simplicity, these may be minor. The description provides enough context for an agent to make a correct call in most situations.

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 input schema has 100% description coverage for the 'id' parameter, so the schema already documents its meaning. The description simply repeats that the JSX is retrieved 'by id' without adding any new syntax, format, or example beyond what the schema provides. At the baseline of 3, this is appropriate since the parameter is fully self‑explanatory in 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 function: 'オリジナルの参照JSXを id で返します' (returns the original reference JSX by id). It specifies a verb (returns), a resource (reference JSX), and the key parameter (id). The additional clause '実在サイトのマークアップではありません' (this is not the markup of an actual site) helps set expectations but does not explicitly differentiate from the sibling tools, many of which also operate on JSX or site-related data. It is more specific than a tautology and provides a clear purpose, though sibling differentiation is left implicit.

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 alternatives. It does not mention any conditions, exclusions, or pointers to sibling tools like get_jp_copy_patterns or get_jp_form_spec. An agent would have to infer usage solely from the tool name and the fact that it expects an id. This is a clear gap given the presence of nine related tools.

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?

No annotations are present, so the description carries the full burden of behavioral disclosure. It clearly reveals the return shape (a list with six named fields), which is meaningful. However, it says nothing about pagination, data volume, ordering, or completeness of the returned list, leaving notable gaps for a list endpoint.

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 Japanese sentence that is front-loaded with the resource and immediately lists the output fields. There is zero wasted text; every element earns its place.

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 list tool with no output schema, the description adequately conveys what is returned and which fields are included. It is missing only minor context such as scale/pagination behavior and how it differs from the search sibling, but the core contract is well covered.

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, and the schema coverage is vacuously 100%, so the baseline of 4 applies. There is no parameter information the description needs to add; the field list it provides pertains to output rather than inputs.

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 verb (返します/returns), a specific resource (日本サイトカタログの一覧), and enumerates the returned fields (url / slug / name / industry / tone / macro), making the tool's job clear. It does not explicitly contrast itself with the sibling search_jp_sites, so it falls just short of full 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?

No guidance is given on when to use this tool versus alternatives. In particular, the relationship to search_jp_sites (list-all vs. search) is left entirely unstated, so an agent cannot decide between them from the description alone.

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?

No annotations are provided, so the description carries the full burden. It discloses that the tool returns many components in one batch, which is useful behavioral context, but it does not mention any limitations, errors, or side effects. The behavior is likely read-only and purely generative, but that is left implicit.

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: one sentence listing the complete output scope and one imperative sentence with usage guidance. Every word serves a purpose, and the most important behavioral instruction ('call this first') is placed at the end for emphasis without padding.

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?

There is no output schema, so the description compensates by enumerating the ten major output categories, which is sufficient for an agent to know what to expect. It could clarify the structure or nesting of results, but the bundle-style behavior and input are adequately covered.

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 input schema already fully documents the single 'brief' parameter with 100% coverage. The description adds that the brief is Japanese but does not specify length, format, or required contents beyond what the schema implies. Baseline score of 3 is appropriate because the schema handles parameter documentation.

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 uses a specific verb ('返します') with a clear resource (日本語ブリーフ) and enumerates a detailed list of outputs, including industry, tone, UI rules, legal, forms, and JSX. It also tells the agent to call this tool first, which distinguishes it from the more specialized sibling 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 phrase '最初にこのツールを呼んでください' explicitly signals this tool is the entry point and should be invoked before other tools. It does not mention when to use alternatives, but the first-call guidance provides clear practical usage context.

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?

With no annotations, the description carries the behavioral burden. It discloses one meaningful behavioral trait: it does not return logos or copy. However, it omits other useful behavior such as result shape, ordering, or pagination details.

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?

Three short, information-dense sentences. The main action is front-loaded, filters are summarized, and the exclusion is given last without wasted words.

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 search tool with no output schema, the description is adequate for selecting and invoking it, but it does not clarify what the returned results contain beyond saying they are not logos or copy. This leaves an important gap for an agent deciding whether the result satisfies the task.

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%, with each parameter already documented as filters or search terms. The description adds only a high-level restatement that industry and tone can be used for narrowing, so it provides little 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 names a specific verb and resource: 語彙検索 of the 日本サイトカタログ. It also states filtering by 業界・トーン and explicitly excludes ロゴや文言, which distinguishes it from copy-focused siblings.

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 clearly implies this is for lexical catalog searches with industry/tone filters. The statement ロゴや文言は返しません provides a useful exclusion, signaling when not to use it, though it does not name alternative sibling tools explicitly.

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