Kids Stay

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

Annotations already indicate readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description adds value beyond annotations by specifying what exactly is returned (verified details, conditions with notes, kids facilities, access, sources, verification date) and constraining output format (text and Markdown links only, no widgets). This matches and supplements the safety profile. No contradictions found.

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, well-structured sentence that front-loads the core purpose ('slug指定で施設の全条件…を返します') and appends the crucial constraint about widget prohibition. Every sentence segment adds unique value with no 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 has one parameter, full schema coverage, and no output schema, the description effectively communicates the return structure (text/Markdown links, no widgets) and content (conditions, kids facilities, access, etc.). For a read-only detail fetcher, it is nearly complete. Minor gap: it doesn't mention pagination or absence thereof, but this is acceptable for a single-slug lookup.

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% for the single parameter 'slug', and the schema already documents it as '施設slug（search_hotelsの結果に含まれる）'. The description does not add new semantic information about the parameter beyond what the schema provides; it just reinforces that the slug comes from search_hotels. 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 specifies a clear verb ('返します' – returns) and resource ('施設の全条件' – all conditions of the facility), enumerating detailed components (note付き条件、キッズ設備、アクセス、出典、検証日). It also explicitly clarifies what the tool does NOT do (no map/location widgets), distinguishing it from potential sibling tools like search_hotels that might provide lists or presentation widgets.

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 implicitly states when to use this tool: after obtaining a slug from search_hotels. It also explicitly forbids adding map/place card widgets, which serves as a clear instruction for the agent. However, it does not provide explicit alternatives or exclusion criteria (e.g., when NOT to use it), missing some guidance relative to siblings like list_areas or list_conditions.

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, idempotentHint, and destructiveHint safely. The description adds context about the actual output content (facility counts, major areas, feature page list), which exceeds 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 short, focused sentences: the first states what it returns, the second states its intended usage. No 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 simple list tool with no parameters and no output schema, the description covers the essential purpose and usage. It provides enough context for an agent to decide when and why to call it, though it doesn't mention pagination or result limits, which are not critical for this type.

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 schema coverage is 100% (vacuously). The description correctly does not discuss parameters, and the baseline for 0-param tools is 4.

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 a list of facilities by prefecture, major areas, and a list of editorial area feature pages. This is a specific verb with resource and distinguishes from siblings like search_hotels.

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 explicitly says it is used for rough targeting before searching ('検索前の当たり付けに使います'), providing clear context for when to use it. It does not explicitly name alternatives, but the pre-search context is clear.

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 cover safe read-only behavior (readOnlyHint=true, destructiveHint=false, idempotentHint=true). The description adds beyond annotations by specifying the returned fields and the completeness of the list ('全定義'), which is valuable given there is no output schema.

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 efficiently states the purpose, scope, and return fields. No filler, front-loaded with the key action, and every phrase adds value.

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 no parameters, no output schema, and strong annotations, the description is fully sufficient: it explains what the tool returns, its scope ('全定義'), and its relevance to search. Nothing important is missing.

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 provides no parameter meanings to clarify. Per the rubric, 0 params yields a baseline of 4; the description adds no misleading info and the tool is simple enough that no further parameter explanation is needed.

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' (returns) and clearly identifies the resource: '子連れ条件の全定義' (all definitions of child-friendly conditions). It also enumerates the included fields (id, label, target age, facility count), which distinguishes it from sibling tools like get_hotel and list_areas.

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 states that these are definitions '検索に使える' (usable in search), providing clear context for when to use the tool. It does not explicitly mention alternatives or exclusions, but among the siblings only this tool deals with conditions, so the usage context is clear.

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, idempotentHint, and non-destructive. The description adds crucial behavioral context: results are returned as bulleted text and Markdown links only (no widgets like maps), the page URL leads to the facility's detail/reservation page, and the facility page itself contains a map (so the agent need not add one). This goes well beyond what annotations provide.

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 (3 sentences) and front-loaded with purpose, then covers important behavioral rules. Every sentence adds essential information: what it does, keyword alternative, output format, and display constraints. No 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?

Given the complexity (8 optional parameters, no output schema), the description adequately covers the tool's purpose, usage patterns, output format, and display rules. It references sibling tools for conditions. Minor gaps: it does not explain sorting options or the default limit, but those are defined in the input schema.

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 baseline is 3. The description adds value by explaining that conditions come from a verified set of 48 types (with reference to 'list_conditions'), and that keyword allows direct hotel name search. This enriches the understanding of 'conditions' and 'keyword' parameters beyond their schema descriptions.

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 Japanese hotels using child-friendly conditions, area, child age, and price, and also supports direct keyword search. It references sibling tool 'list_conditions' and distinguishes itself from 'get_hotel' and 'list_areas' by being the primary search 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 explains when to use keyword search (when hotel name is known) vs. other criteria, and directs users to 'list_conditions' for condition IDs. It does not explicitly exclude using this tool when a specific hotel ID is known (which would call for 'get_hotel'), but the sibling context makes the distinction clear.

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