Server Quality Checklist

Tool Scores

• shindo_meaningA
  3.9/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and idempotentHint=true, so the description does not need to restate safety. It adds useful context about using the official 気象庁 scale, but it does not describe the output format, possible disclaimers, or how the Nankai scenario fact relates to the returned explanation. This is acceptable but not rich behavioral detail.

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

  Conciseness4/5

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

  The description is brief and the first sentence is directly informative. The second sentence about the Nankai scenario adds contextual relevance but is somewhat tangential to the core tool function; it is not excessive but not perfectly zero-waste either.

  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 simple, read-only explanation tool with fully documented schema parameters and safe annotations, the description provides adequate context: what the tool explains, the scale used, and the scenario relevance. It does not detail return values, but the verb 'Explain' implies textual output, and no output schema exists, so this is not a major gap.

  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?

  The input schema has 100% description coverage for both parameters (shindo and language) with enums and clear titles, so the schema carries the parameter semantics. The description only loosely echoes the intensity range ('5弱–7') without adding new parameter-level guidance, such as how the 'language' parameter affects output.

  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 clearly states a specific action ('Explain what... means') on a specific resource (JMA seismic intensity levels) and explicitly covers the scope ('for people and buildings'). It distinguishes the tool's explanatory purpose from sibling tools like nankai_overview or official_hazard_maps by emphasizing the meaning of intensity levels rather than overviews or maps.

  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 implies when to use the tool: when one needs to understand the practical meaning of a JMA intensity level (5弱–7) for people and buildings. It does not explicitly mention alternatives or exclusions, but the context is clear enough that an agent can infer appropriate use, especially given the official-scale reference.

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

• official_hazard_mapsA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare read-only, open-world, and idempotent behavior. The description adds meaningful context: it does not compute hazard values itself but links to authoritative sources, and mentions the types of values embedded in those maps (predicted intensity, tsunami inundation). It does not address error cases or link format, but the added context goes beyond 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 two sentences, front-loaded with the action and resource, and each sentence earns its place: the first states the core function, the second clarifies the server's bridging role. No wasted words.

  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 simple tool without an output schema, the description explains what is returned (links to official hazard maps with specific value types) and explicitly sets expectations about the server's own computation. It is nearly complete, though it could mention the response structure or behavior on undeliverable addresses to fully compensate for the missing output schema.

  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?

  The input schema has 100% coverage with descriptions for both parameters ('address' and 'language'), including an example and enum. The tool description does not add parameter-specific meaning beyond the schema, and with full schema coverage, a baseline of 3 is appropriate.

  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 clearly identifies the tool's function: geocoding a Japanese address and returning links to official government hazard maps. It distinguishes itself from siblings by explicitly stating it bridges to authoritative sources rather than computing hazard values, differentiating from tools like building_seismic_check or nankai_overview.

  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 implies when to use this tool: when exact per-address official values are needed. It also clarifies what the tool does not do (compute hazard values), which helps rule out alternatives. However, it does not explicitly name alternative tools for different scenarios, such as geocode_address for plain geocoding or nankai_overview for regional overviews.

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

• nankai_overviewA
  4.3/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds that the tool provides sources and is an overview, but does not disclose additional behavioral traits such as response format, pagination, or any caveats. It does not contradict annotations, but adds limited behavioral context beyond them.

  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 long, front-loaded with the primary result and a clear usage pointer. Every sentence earns its place: the first explains what the tool returns, the second explains when and how to proceed. No redundancy or filler.

  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?

  There is no output schema, so the description must convey the return value. It lists the key facts (probability, casualties, intensity-7 reach, tsunami) and mentions 'with sources', giving the agent a clear expectation. For a simple overview tool with one optional parameter and strong annotations, this is sufficiently complete.

  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?

  The schema provides 100% coverage for the single 'language' parameter with an enum and description. The tool description does not add any additional parameter semantics beyond what the schema already conveys, so the baseline score of 3 is appropriate.

  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 'get' and identifies the resource as 'headline facts of the official 2025 Nankai Trough estimate', listing the content areas (probability, casualties, intensity-7 reach, tsunami) and sources. It clearly distinguishes itself from sibling tools by positioning as the starting point and even pointing to the next tool to call.

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

  Usage Guidelines5/5

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

  The description explicitly states when to use it: 'Start here to understand the scale' and then instructs to call official_hazard_maps for a specific address. This provides clear usage context, a sequential workflow, and an alternative tool for a different use case.

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

• taishin_subsidy_guideA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare read-only and idempotent, and the description adds useful behavioral context: it uses the national directory, explains the support framework, and deliberately avoids quoting figures. This goes beyond the annotation metadata without contradicting it.

  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 focused sentences, front-loaded with the main action and followed by one meaningful constraint. No wasted words.

  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 low-complexity tool with no output schema and two optional, well-described parameters, the description covers the core behavior, the route vs. quote distinction, and municipal variability. An agent has enough context to select and invoke this tool appropriately.

  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?

  The 100% schema description coverage means the language and location parameters are already fully explained in the schema. The description adds no parameter-specific details, so a baseline of 3 is appropriate.

  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 specific verbs ('Route', 'explain') and names the exact resource ('subsidised/often-free seismic diagnosis... programs via the national directory'). It clearly distinguishes this from siblings like building_seismic_check by framing it as a subsidy guidance tool rather than a structural assessment tool.

  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 defines the tool's role as routing/explaining and explicitly warns it 'never quotes a figure', telling an agent when not to rely on it for specific amounts. It does not explicitly name sibling tools, but the context makes the intended use case clear.

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

• building_seismic_checkA
  4.4/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint and idempotentHint, so the description doesn't need to restate safety. It adds behavioral context by mentioning 'risk context' and clarifying the tool is not a verdict, plus a referral action. 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.

  Conciseness5/5

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

  Two concise sentences: the first states the core action and inputs, the second adds a caveat and referral. Every word earns its place without redundancy.

  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?

  There is no output schema, but the description conveys the classification output and its limitations sufficiently for an agent to decide and redirect. It doesn't detail return format, but the core purpose and boundary are clear, and schema covers parameters.

  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% with each parameter having a description. The description only restates 'build year and structure' without adding new meaning; the schema already provides details on enums and ranges.

  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 the specific verb 'Classify' and identifies the resource ('building's seismic standard') with named classification types (旧耐震 / 新耐震 / 2000 wooden standard). It also distinguishes from siblings by explicitly stating 'This is NOT a safety verdict' and referencing taishin_subsidy_guide.

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

  Usage Guidelines5/5

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

  The description gives explicit when-to-use context: 'from a build year and structure the USER provides'. It also provides when-not-to-use ('NOT a safety verdict') and a specific alternative ('direct the user to a professional 耐震診断 via taishin_subsidy_guide').

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

• geocode_addressA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds useful context about the official GSI geocoder and its relationship to official_hazard_maps, providing extra behavioral framing without contradicting 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 two sentences, front-loaded with the core action, and provides sibling context without unnecessary fluff. Every clause contributes to understanding the tool's purpose and usage.

  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?

  The tool is simple with a single parameter, no output schema, and meaningful annotations. The description covers the main purpose, the external geocoder, and the scenario for direct use. It does not mention output format details, but for a simple geocoding tool this is acceptable.

  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% as the 'address' parameter includes its own description. The tool description repeats the parameter's purpose without adding extra semantic detail like formatting or examples. However, it does clarify that the address must be Japanese, which is slightly beyond the schema.

  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 clearly states the specific verb 'Convert' with the resource 'a Japanese address' and the output (coordinates and prefecture/municipality). It also distinguishes from siblings by noting it's a utility used by official_hazard_maps, making its role unambiguous.

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

  Usage Guidelines5/5

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

  The description explicitly says 'call it directly when you only need coordinates', which indicates when to use this tool versus relying on official_hazard_maps. It also implies that official_hazard_maps is the higher-level alternative.

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