Server Quality Checklist

Tool Scores

• get_hotelA
  4.3/5.0
  Behavior4/5

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

  Annotations already establish the safe read-only, idempotent, non-destructive profile, and the description adds useful behavior: the response contains evidence notes, sources, and a verification date, and the output rendering must be text/Markdown only with no map or place-card widgets. No contradiction with the annotations exists.

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

  Conciseness5/5

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

  The description is two sentences with no filler: the first front-loads the retrieval purpose and contents, and the second gives a crisp rendering constraint. Every sentence earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

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

  With one required parameter, no output schema, and read-only/idempotent annotations, the description covers everything an agent needs: what is returned, how it is selected, and how it must be presented. The absence of detailed response formatting is acceptable given the low complexity of the tool.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, and the schema already explains that slug is the facility slug included in search_hotels results. The description only repeats 'slug指定' and adds no additional parameter meaning, so the baseline 3 applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

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

  The description states a specific action ('返します') and a concrete resource: facility conditions with per-facility evidence notes, kids' equipment, access, sources, and verification date, retrieved by slug. This clearly differentiates it from the sibling search/list tools, which operate at a different level of granularity.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives clear context: call it with a slug to get the full verified detail payload, and then present the result as text/Markdown links without widgets. It does not explicitly name alternatives or state when not to use it, so it stops short of full routing guidance.

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

• list_areasA
  4.3/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, so the safety profile is covered. The description adds that it returns counts and feature pages, and the phrase '主要エリア' hints at a possible scope limitation. However, it does not disclose return format, pagination, or data freshness; with no output schema, this is a moderate gap.

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

  Conciseness5/5

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

  A single sentence that front-loads the return content and closes with the intended use case. No filler or redundant restatement of the title.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

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

  This is a parameterless read-only list operation with strong annotations. The description fully specifies what it returns and when to use it; no invocation complexity is missing. An agent can confidently call and interpret this tool without further documentation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema has zero parameters and 100% schema description coverage, so there is nothing for the description to compensate for. Baseline for 0 params is 4; no additional parameter detail is needed.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  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) and a concrete resource: prefecture-level facility counts, major areas, and editorial area feature page list. It also frames the tool as a pre-search rough targeting aid, which distinguishes it from search siblings. This is above the minimum viable and leaves no ambiguity about what the tool does.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description explicitly says to use it before searching for rough targeting (検索前の当たり付けに使います), providing clear context for when to invoke it. It does not explicitly name sibling tools or give exclusions, so it stops just 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.

• list_conditionsA
  4.3/5.0
  Behavior3/5

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

  The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety and side effects. The description adds that the tool returns all definitions and enumerates the fields, which is consistent but does not introduce significant behavioral traits beyond what the 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.

  Conciseness5/5

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

  A single, front-loaded sentence that states the purpose first and packs the return fields into a parenthetical list. There is no filler or redundant information; every part of the sentence earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

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

  For a simple parameterless listing tool, the description tells the agent exactly what will be returned and why it exists. The absent output schema is compensated by the explicit field list, and annotations cover operational behavior, so nothing essential is missing.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The tool has zero parameters and an empty schema, so there are no parameter semantics to document. The description's emphasis on '全定義' (all definitions) confirms the tool takes no filters and returns the complete set, which is appropriate for this zero-parameter design.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  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 a precise resource ('子連れ条件の全定義' – all definitions of child-friendly conditions), and it lists the return fields (id, label, target age, facility count). This clearly distinguishes it from sibling tools like list_areas and search_hotels, which are about areas and hotel search rather than condition meta-definitions.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The phrase '検索に使える' (usable for search) provides clear context that this is a reference list intended to be used with search_hotels. It does not explicitly name alternatives or state exclusions, but the intended usage context is clear enough for an agent to infer when to call this tool.

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

• search_hotelsA
  4.6/5.0
  Behavior5/5

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

  Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds meaningful behavior: results are limited to bulleted text and Markdown links, no map/location-card widgets should be attached, and each result's page URL is the facility's detail/reservation page. It also notes conditions are verified, which is useful operational context 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.

  Conciseness5/5

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

  The description is compact and front-loaded: purpose first, then the keyword shortcut, then output and display constraints. Every sentence carries distinct information and there is no redundant repetition of the schema or annotations.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

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

  For a read-only search tool with 8 optional parameters and no output schema, the description covers the search dimensions, condition-source reference, keyword behavior, result URL meaning, and output formatting. It does not explicitly mention list_areas for valid area values or get_hotel for single-hotel detail lookup, and it does not address empty-result handling, but the schema and annotations cover much of the remaining context.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema covers all 8 parameters with descriptions and examples (100% coverage), so the baseline is 3. The description adds extra value by tying conditions to the 48 verified IDs in list_conditions and clarifying that keyword is for direct hotel-name search, which goes slightly beyond the schema text.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

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

  Description clearly states it searches Japanese accommodations using verified baby/child-friendly conditions (48 types, referencing list_conditions), area, child age, and price. It distinguishes itself from siblings by emphasizing condition-based search and keyword search when the hotel name is known, so an agent can tell it apart from get_hotel/list_conditions/list_areas.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Gives clear guidance on when to search by conditions/area/age/price and when to use keyword directly if the hotel name is known. It also points to list_conditions for valid condition IDs and gives output formatting rules. It does not explicitly direct the agent to get_hotel for a single hotel's details or state when not to use this tool, which keeps it 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.