Japan Real Estate Intel

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description's main added value is the geographic restriction (Nagoya) and the 'future plan upside' feature. It doesn't disclose any additional behavioral traits such as estimation methodology, error handling, or whether results are approximate. With annotations covering safety, this is acceptable but not rich.

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 concise sentences with the primary purpose front-loaded. It avoids redundancy and quickly conveys the tool's scope. Minor improvement could be adding explicit output format details, but as a description it is efficient.

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 no output schema, so the description must explain what the agent can expect. It lists the computed outputs (acquisition cost, renovation cost, rent, yields) but does not specify the structure, units, or whether results are estimates. Given the tool's complexity and lack of output schema, more detail would be needed for full 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?

Schema description coverage is 100%, so all parameters are defined in the schema. The description doesn't add per-parameter details beyond the schema, but it does frame how the inputs combine (e.g., acquisitionPrice is optional and estimated when omitted). This is a marginal addition over the schema, hence the baseline 3.

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 calculates acquisition cost, renovation cost, expected rent, and gross/net yield for Nagoya neighborhoods, with a note on future plan upside. It differentiates from siblings like recommend_renovation_targets by focusing on yield analysis rather than recommendations, though it doesn't 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?

The description does not provide any guidance on when to use this tool versus alternatives. It only states the general purpose and geographic scope, leaving the agent to infer whether this is the right choice based on the need for yield calculations. No mention of exclusions or conditions that would route the agent elsewhere.

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 destructiveHint=false, so the safety profile is covered. The description adds the behavior that it returns a risk score and deal-breakers, which is the core functionality. However, it does not disclose any additional behavioral traits such as how the score is computed, whether location parameters matter, or any limitations. With annotations covering safety, the description provides minimal extra context, earning a 3.

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, information-dense sentence front-loaded with the purpose and specific parameters. It is free of filler and provides the essential information in a compact form. The addition of a Japanese translation is a minor structural duplication but does not detract from its conciseness. It earns a 5 for efficiency and clarity.

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's moderate complexity (3 parameters, one nested object) and the absence of an output schema, the description adequately states the input (proposed clauses) and output (risk score + deal-breakers). It does not explain how the location parameters (ward, chochou) factor into the assessment, nor does it mention any prerequisites, but the schema covers the parameters and the purpose is clear. Considering the sibling landscape, it could benefit from noting when to use this versus 'assess_property_risk', but that is already covered under usage guidelines. Overall, it is complete enough for an agent to call it correctly, so a 4 is justified.

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 adds value by listing concrete clause types ('financing contingency, inspection, future value terms') that clarify what should go into the 'proposedTerms' object, which the schema only describes generically as '提案中の契約条項（JSON 形式）'. This goes beyond the schema and helps the agent populate the parameter correctly. It does not elaborate on 'ward' or 'chochou', but those are self-explanatory with their own schema descriptions, so a 4 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 a specific action ('analyze proposed clauses') and resource ('contract risk'), and specifies the output (risk score and deal-breakers). It goes beyond a tautology by naming example clause types (financing contingency, inspection, future value terms). However, it does not differentiate this tool from the sibling 'assess_property_risk', which could be confused; thus not a 5.

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 offers no explicit guidance on when to use this tool versus alternatives. It does not mention any conditions, exclusions, or mention of sibling tools like 'assess_property_risk' or 'generate_contract_support_package'. The usage context is only implied by the tool's name and purpose, so it fails to provide actionable direction for 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description's 'Assess' action aligns with this. The description adds scope details (3 axes, 10 prefectures) but does not disclose return format, error behavior, or limitations. Since the annotations carry the safety profile, the description adds some value but not rich behavioral context, earning a 3.

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 brief and front-loaded: it states the verb and scope in the first clause, followed by the axes and scale. The Japanese duplicate is redundant for English-reading agents but does not harm. No wasted sentences, and the structure is efficient.

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?

With 6 parameters, one required, a nested object, no output schema, and no parameter explanations, the description is insufficient. It does not clarify what 'area' refers to (prefecture vs. arbitrary region), which prefectures are covered, or what the output looks like. An agent would need to infer too much to call this tool correctly.

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 67%, and the description adds no parameter-specific information. It does not explain what 'area' means, how latlng or childAge are used, or how the optional parameters affect the assessment. The description leaves parameter semantics entirely to the schema, which is only partially documented. Since coverage is below 80%, the baseline is raised, but the description does not compensate.

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's purpose: 'Assess family-friendliness' with specific axes (education, safety, healthcare) and a scope (10 prefectures). It is not a tautology and gives a distinct functional identity. However, it does not explicitly differentiate from sibling tools like compare_prefectures or drill_down_local_analysis, which could also involve area assessment.

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 states what it does but does not mention any conditions, exclusions, or situations where another sibling tool would be more appropriate. An agent gets no context for selection beyond the tool's name.

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 destructiveHint=false, which cover the safety profile. The description adds meaningful behavioral context: it integrates scoring across risk types, supports exactly 10 prefectures, and provides a bilingual clarification. This goes beyond what annotations state, informing the agent about the scope and the nature of the output (integrated score). No contradiction with annotations; the description aligns with the read-only nature.

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 exceptionally concise: two clear sentences (one English, one Japanese) that convey the purpose and a key limitation. It front-loads the core function before revealing the geographic scope. Every word adds value, with no redundant or filler content. The bilingual pair is a compact way to ensure international usability without sacrificing clarity.

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 tool with 5 parameters, a nested object, and no output schema, the description covers the main purpose and geographic scope but leaves several operational gaps. It does not explain how to choose between address and latlng, whether both can be used, or what the output format looks like (e.g., a score per risk type or a single integrated score). It also does not mention that riskTypes defaults to 'all'. While the description is adequate for a basic understanding, it lacks details that would help an agent correctly construct the input, especially for the optional parameters. A 3 reflects that it is functional but incomplete.

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?

With schema description coverage at 60%, some parameters (address, prefecture, neighborhood) have schema descriptions, while latlng and riskTypes lack explicit descriptions in the schema. The description helps by listing the three risk types (flood, landslide, earthquake), which maps to the riskTypes parameter, and mentions 'integrated scoring' which implies how riskTypes are combined. However, it does not clarify the relationship between address and latlng (e.g., are they mutually exclusive? which takes precedence?), nor does it explain the default behavior of riskTypes (default is ['all']). The description adds some value but does not fully compensate for the uncovered parameters, so a baseline 3 is justified.

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 ('assess'), a resource ('property disaster risk'), and enumerates the risk types (flood, landslide, earthquake). It also specifies the integrated scoring across 10 prefectures, which differentiates it from siblings that focus on other aspects (e.g., compare_prefectures for comparison, assess_contract_risk for contracts). The purpose is unambiguous and distinguishes the tool from its siblings without needing to inspect the schema.

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 the tool is for evaluating disaster risk on a property, but it does not explicitly state when to use this tool versus alternatives. It mentions the geographic scope ('10 prefectures') which hints at a limitation, but does not provide explicit conditions or exclusions (e.g., 'use only for these prefectures, otherwise see X'). Usage guidance is implied rather than clearly articulated, so a 3 is appropriate.

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 destructiveHint=false, so the safety profile is covered. The description adds 'Markdown output' and 'ranking' context, but does not mention the json/xlsx export options or that xlsx returns a base64 field; those are only in the schema. No contradiction 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 a single clear sentence (plus a Japanese translation) that front-loads the purpose, scope, and metric list. There is no filler, though the redundancy of listing metrics twice adds a little length.

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?

With 7 parameters and no output schema, the description is under-specified. It does not explain the response structure, the xlsx base64 behavior, or how neighborhood/propertyType affect the comparison. An agent would have to rely on the schema alone, which is incomplete at 57% coverage, to call this tool correctly.

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 57% (above 50%), so baseline is 3. The description maps metrics to land price, population, risk, and investment, which partially explains the 'metrics' parameter, but it does not add clarity for propertyType, includeMarkdown, or neighborhood. The 'Markdown output' claim conflicts with the default exportFormat of 'json' in the schema, a minor semantic inconsistency.

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 ('Compare') and resource ('prefectures'), with a concrete scope ('up to 5') and a list of metrics (land price, population, risk, investment score). This clearly differentiates it from sibling tools like composite_value_score or cross_analyze_real_estate_market, which target different analyses.

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 usage when comparing prefectures across the listed metrics, but does not explicitly mention when not to use it or point to alternatives. There is no exclusions or routing guidance, making it adequate but not strong.

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 destructiveHint=false, so the safety profile is covered. The description adds the fusion semantics and output artifacts. However, it advertises 'AI narrative' without disclosing the Gemini API-key dependency that the includeNarrative parameter documents, which could mislead an agent into expecting the narrative to always succeed. Not a contradiction, but a modest disclosure gap given the output feature is prominent.

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?

Two sentences (English plus a Japanese translation) with the core purpose front-loaded and no filler. The bilingual duplication costs some economy, but it is reasonable for a Japan-market tool and every sentence 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?

An output schema exists, so return-value documentation is unnecessary. The description covers the fusion model and output artifacts. Missing pieces: no usage guidance versus siblings, no disclosure of the narrative API dependency, and no clarification of weight semantics (e.g., whether weights must sum to 1). Adequate for a schema-rich tool but not 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?

Schema description coverage is 100%, with every parameter documented including enums, ranges, defaults, and bilingual notes. The description's mention of the 5 axes merely restates what the weights object already documents. It adds no param-level meaning beyond the schema, so the baseline 3 for full coverage 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 states a specific verb ('fuse') and a concrete resource (5 named axes into a 0-100 score), and previews the output artifacts (radar, tier, peer comparison, AI narrative). It is clear what the tool does. However, with 30+ siblings it never names what it is not — an agent cannot readily tell it apart from assess_property_risk, forecast_land_price_trend, or cross_analyze_real_estate_market without opening schemas.

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 when-to-use guidance, no exclusions, and no alternative routing is provided. Given the large sibling set and overlapping analysis tools (assess_property_risk, cross_analyze_real_estate_market, compare_prefectures), an agent has no signal about which tool fits a given query. The purpose is stated, but the choice context is entirely absent.

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, openWorldHint=false, and destructiveHint=false, so safety is covered. The description adds the 10-prefecture scope constraint, which is mildly useful context. However, it gives no details about data sources, update frequency, or limitations beyond the prefecture count. With annotations doing most of the work, a 3 is appropriate.

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, repeated in Japanese for bilingual support. It front-loads the core function and factors, with no filler. The only redundancy is the translation, which is purposeful. It is well-structured for its length.

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 14 parameters, 3 required, and no output schema. The description is too brief to cover the complexity: it does not explain what the output looks like, which factors are always included, how the 'investment score' is computed, or what '10 prefectures' means. An agent would likely need to inspect the schema and possibly call the tool to fully understand its behavior.

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 79%, so the schema explains most parameters. The description mentions the five analysis factors, which loosely map to include flags (e.g., includeHumanFlow, includeEducation), but it does not explicitly explain any parameter. It adds minimal value beyond what the schema already provides, so the baseline 3 holds.

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 (cross-analyze) and resource (real estate market) with a clear list of factors (land price trends, investment score, foot traffic, education, corporate presence) and scope (10 prefectures). It is clear but does not explicitly distinguish itself from sibling tools like 'compare_prefectures' or 'drill_down_local_analysis'.

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 conditions, prerequisites, or scenarios where a sibling tool would be more appropriate. Usage must be inferred entirely from the name and vague description.

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 destructiveHint=false, so the description correctly reflects a non-mutating scan. It adds the core behavioral detail—triangulating three price sources to compute signals—which is beyond annotations. However, it does not mention data freshness, staleness, or the fact that includeLive requires an API key (that is left to the schema). For a read-only tool, the description adds moderate context but not rich operational caveats.

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?

Two tightly written sentences, with the core purpose and key signals front-loaded. The bilingual repetition is intentional and adds no fluff. Every word earns its place, and there is zero 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 read-only scanner with full parameter descriptions and an output schema, the description covers the central function and signal categories. The main gap is the lack of usage guidance relative to siblings, and it doesn't touch on operational constraints like data licensing or API-key requirements (though those are hinted in the includeLive parameter schema). Overall it is adequate but not exhaustive for a tool with 5 parameters and many siblings.

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 every parameter is already documented in the input schema. The description adds value by mapping signal types (discount, inheritance_edge, overheated) to the tool's purpose, which clarifies the meaning of signalType. However, it doesn't elaborate on output_mode or limit beyond what the schema provides, so the added value over the schema is modest.

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 and resource: 'Price triangulation arbitrage scanner' that cross-checks three named data sources (rosenka, koji, tx) and produces three concrete signal types. This clearly distinguishes it from sibling tools like discover_opportunities or composite_value_score, which target different analytical angles.

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 what the tool does but never states when to prefer it over alternatives, nor does it give exclusions or conditions. Sibling tools like discover_opportunities or cross_analyze_real_estate_market overlap in domain, yet no routing guidance is provided. An agent would have to infer usage from the tool name 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?

Annotations already cover readOnlyHint=true and destructiveHint=false, so the description's burden is lowered. It adds the behavioral trait of 'multi-source scoring' and hypothesis-card generation, which is genuine context beyond annotations. However, it does not disclose API-key-gated behavior (MLIT/Gemini) or anything about how scoring aggregates sources, leaving some behavioral detail unstated.

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 core info ('scan a prefecture + goal + hypothesis cards') is front-loaded in the first sentence, which is good. But the entire English text is duplicated verbatim in Japanese, roughly doubling the length without adding information. This bilingual redundancy is wasteful, though not egregious.

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?

An output schema exists, so return values are covered. However, with 10 parameters and only 70% schema coverage, the description should clarify the compact-vs-detailed output_mode behavior and the API-key-dependent features (useGeminiNarrative, includeExternalFreshness), neither of which is addressed. The description is adequate for the core use case but under-specifies the tool's optional, conditional behaviors.

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 70% (goal, limit, prefecture, budgetLevel, output_mode, useGeminiNarrative, includeExternalFreshness have descriptions; horizon, riskTolerance, includeMarkdown do not). The description's only param contribution is restating goal values (investment/store/family/office/development), which are already enumerated in the goal enum in the schema. The description adds no meaning for the three undocumented parameters, so it fails to compensate where the schema is silent.

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 a specific verb ('scan') applied to a resource ('prefecture') with explicit goal types (investment/store/family/office/development) and describes the output format ('hypothesis cards with multi-source scoring'), which distinguishes it from area-report and drill-down siblings. However, no sibling is named explicitly, so the distinctiveness relies on the reader inferring the difference from the output type rather than a stated boundary.

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 explicit when-to-use, when-not-to-use, or alternative-tool guidance. The phrase 'scan a prefecture for undervalued areas' implies a discovery use case, but there is no exclusion of cases where search_area_candidates or drill_down_local_analysis would be more appropriate, which matters given 31 siblings including several area-search 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, covering safety. The description adds that output is in Markdown, but this is partly redundant with the exportFormat parameter. It does not disclose limitations such as supported prefectures (hinted in the neighborhood param description) or data freshness.

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 concise sentences, front-loading the purpose and scope. The bilingual repetition in the second sentence adds no new information but is not disruptive. Overall it is efficient and avoids unnecessary verbosity.

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?

With no output schema, the description should clarify what the tool returns, but it only states 'Markdown output' without explaining the structure or that exportFormat can also produce JSON/XLSX. It also omits prerequisites like supported prefectures, though this is partially covered in the 'neighborhood' parameter description. The description is adequate for basic orientation but lacks 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?

Schema description coverage is 80%, with 'focus' lacking any description. The tool description adds no parameter-specific semantics; it merely repeats the output format. While the schema covers most parameters, the gap for 'focus' is not compensated, so the description provides little added value.

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 a specific action (drill-down analysis) and resource (block/neighborhood level), listing the data domains covered (foot traffic, commercial, education). This distinguishes it from area-level tools like compare_prefectures or generate_area_report, making the purpose unambiguous.

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 granular, local analysis via the phrase 'at block/neighborhood level', but does not explicitly instruct when to use this tool versus siblings or when not to. No alternatives are mentioned, leaving the agent to infer suitability based on scope.

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, non-destructive, and non-open-world behavior. The description adds the constraint of '10 prefectures' and the Japanese text mentions that a score is calculated. However, it does not disclose any other behavioral traits such as rate limits, side effects, or output format beyond the score mention.

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 extremely concise, two short sentences in English plus a Japanese translation, and the key purpose is front-loaded. Every word earns its place; there is no fluff 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?

Given the tool's complexity (7 parameters, nested objects, no output schema), the description is too brief. It does not explain what the tool returns (beyond a vague 'score' in the Japanese text), does not list the 10 prefectures, and provides no caveats or prerequisites. An agent would not know the full scope or output format from this description alone.

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 86%, so the parameters are already well-documented in the schema. The tool description does not add any parameter-specific meaning beyond what the schema provides. With such high coverage, a baseline of 3 is appropriate, and the description neither enhances nor detracts.

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 clear verb ('Evaluate') and resource ('store location suitability'), listing specific considerations (foot traffic, transport, competitor distribution). It does not explicitly differentiate from sibling tools, but the subject matter is distinct enough that an agent can infer its use. The '10 prefectures' constraint adds scope.

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 purpose implies usage (evaluate a potential store location), but there is no explicit guidance on when to use this tool versus alternatives, nor any stated exclusions or prerequisites. The mention of '10 prefectures' hints at a coverage limit but does not clarify which ones or when to switch to another tool.

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 destructiveHint=false, so the safety profile is fully covered. The description adds the return format (Markdown) and the content categories, which is useful behavioral context beyond the annotations, but it does not disclose error behavior, rate limits, or pagination.

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?

Two short sentences with the key verb and resource front-loaded. The bilingual duplication is redundant but not harmful; the English portion conveys the essential information efficiently without unnecessary 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 single-parameter read-only tool with no output schema, the description adequately explains what to provide (a search result ID) and what to expect (Markdown with analysis, forecasts, summaries). It doesn't cover edge cases or error handling, but these are minor for a straightforward fetch operation.

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%: the id parameter has a description that references the search tool and provides an example. The description itself only repeats 'by ID from search results', adding no new semantic detail beyond what the schema already provides, so it meets 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 verb (Fetch), resource (full document by ID), and the content it returns (area analysis, forecasts, summaries). It clearly ties itself to search results, distinguishing it from the many analysis and simulation siblings by indicating it is the retrieval step after a search.

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 explicitly says the ID comes from search results, and the schema parameter description reinforces this by naming the search tool and giving an example format. However, it does not mention when not to use it or compare it to alternative tools, so the guidance is clear but not exhaustive.

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 destructiveHint=false, which covers the safety profile. The description adds useful context by stating the return values (CAGR, confidence interval, investment signal) and the 10-prefecture restriction. However, it does not disclose assumptions, data sources, or failure modes (e.g., what happens for unsupported cities), so it adds some but not rich behavioral detail 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.

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

The description is efficiently written with two short sentences in English and Japanese, front-loading the core purpose and primary outputs. It avoids unnecessary filler words. The bilingual repetition is redundant but not wasteful. It earns a 4 for being concise and focused.

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?

With no output schema, the description correctly lists the return values (CAGR, confidence interval, investment signal), and it notes the 10-prefecture limitation. However, it omits any mention of parameter constraints beyond scope (e.g., city format, required prefecture), assumptions for forecasting, or how to interpret results, which an agent might need for confident invocation. It covers the essentials but leaves some 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 description coverage is 86%, and the schema already documents all parameters with meaningful descriptions (e.g., method enum values, output_mode details). The description reinforces the method choices (linear regression, moving average) and partially explains the scope ('10 prefectures'), but it does not add significant new meaning beyond the schema. It stays at the baseline expected 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 verb ('Forecast') and resource ('land price trends') along with specific outputs (CAGR, confidence interval, investment signal). It distinguishes itself by mentioning the statistical methods (linear regression, moving average) and the 10-prefecture scope, which differentiates it from siblings like compare_prefectures or simulate_aichi_future, though it doesn't 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?

No guidance is provided on when to use this tool versus alternatives. It does not mention exclusions, contexts, or reference any sibling tools. While the scope ('10 prefectures') hints at coverage constraints, there is no explicit when-to-use or when-not-to-use guidance, leaving the agent to infer suitability.

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 destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context: it is limited to 10 prefectures and supports branding via parameters like companyName/agentName. However, it does not disclose return format details (e.g., that PDF returns a base64 field) beyond what the schema mentions, nor any other behavioral traits.

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 short sentences in English and their Japanese translation. The core purpose is front-loaded. The bilingual duplication adds length but the content is minimal and not verbose; it sacrifices some compactness for clarity, which is acceptable.

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 tool with 13 parameters and no output schema, the description is too sparse. It does not explain what 'comprehensive' includes, what the purpose options mean, or how this differs from similar report tools. The scope limitation to 10 prefectures is noted, but the description lacks the depth needed for an agent to decide when this tool is appropriate and what to expect beyond the 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 description coverage is 77%, so the baseline is 3. The description adds a small amount of parameter context (branding support, 10 prefectures) but does not explain the required 'area' and 'purpose' parameters beyond what the schema provides. Since most parameters have inline descriptions, the description's contribution is marginal, keeping the score at 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 clear verb and resource: 'Generate comprehensive area report in Markdown/PDF with branding support.' It immediately indicates the output formats and branding capability. The mention of '10 prefectures' scopes the resource, and while it doesn't name a sibling, the purpose is distinct enough from analysis tools like 'compare_prefectures' or 'quick_visual_summary' to be unambiguous.

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 gives no guidance on when to use this tool versus alternatives. It does not mention any sibling tools, nor does it state prerequisites or conditions for selection. The reader is left to infer that this is the tool for generating reports, but no explicit usage context is provided.

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 destructiveHint=false, so the safety profile is known. The description adds the output format (Markdown + branded PDF), which is useful, but it does not disclose any other behavioral traits such as whether the tool generates files, requires external services, or has rate limitations. Beyond the output format, it adds little 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.

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

The description is concise, with the core purpose and deliverables front-loaded. The bilingual inclusion (English + Japanese) doubles length but likely serves the target audience; it's not verbose, and every sentence contributes to understanding the tool's output.

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?

With 7 parameters, no output schema, and a generation-style tool, the description should clarify what 'package' means structurally and when to use it vs. simpler assessment tools. It mentions output formats but not the package's contents or any limitations. Given the complexity and lack of output schema, the description is adequate but not fully 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?

Schema description coverage is 100%, so all seven parameters have in-schema descriptions. The description's phrase 'from neighborhood/property data' loosely ties to the parameters but doesn't add any per-parameter meaning beyond the schema. As baseline for full coverage, a score of 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 states a specific verb ('generate') and resource ('contract support package'), and enumerates concrete deliverables (risk matrix, price negotiation anchors, recommended clauses). It differentiates from sibling tools like assess_contract_risk or assess_property_risk by framing the output as a consolidated package rather than a single assessment.

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 usage context ('from neighborhood/property data') and output format (Markdown + branded PDF), but it does not explicitly state when to choose this tool over alternatives like assess_contract_risk for a lighter analysis, nor does it mention any exclusions. The guidance is implicit rather than explicit.

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 destructiveHint=false, so the safety profile is covered. The description adds 'current metrics' and specifies data types, but does not disclose output format, pagination, or any other behavioral traits. With annotations in place, the description provides marginal additional 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 concise with one English sentence and one Japanese duplicate, effectively front-loading the purpose. The duplication is somewhat redundant but not harmful. It earns a 4 for efficiency despite the minor 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 tool with one required parameter and optional granularity, the description is adequate but lacks usage differentiation from the many sibling tools. No output schema exists, so better guidance on what the response contains would be helpful, but the metric list partially covers this. Overall, it is sufficient but not 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?

Schema description coverage is 100%, so all three parameters (ward, chochou, output_mode) are fully documented in the schema. The description does not add extra meaning beyond what the schema already covers, so the baseline of 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 a neighborhood profile with specific current metrics (land price, population, households, ongoing plans) for Nagoya wards/neighborhoods. This is a specific verb+resource with explicit data categories, distinguishing it from siblings that focus on trends, forecasts, or analysis.

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 provided on when to use this tool versus alternatives like generate_area_report, drill_down_local_analysis, or get_population_outlook. The description does not mention context, prerequisites, or exclusions, leaving the agent to infer the appropriate use case.

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 destructiveHint=false, so the description does not need to repeat safety. It adds context that the output is an 'annual timeline' (年次タイムライン) and covers future plans, but does not detail pagination, error behavior, or data structure. Given the annotation coverage, this is adequate but not rich.

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 sentences (English and Japanese) with zero filler. Key information—subject, scope, time range, and return format—is front-loaded. Every word earns its place, making it highly efficient.

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 tool with no output schema, the description states it returns an 'annual timeline' of future plans, which partially explains the return. However, it lacks detail on the structure (e.g., whether results are grouped by year, include event types, or provide coordinates). Given the complexity of future-plan timelines, an agent might need more specifics, though the safety annotations reduce risk.

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% for both 'ward' and 'chochou', so the schema already documents parameter meanings. The description adds contextual value by linking parameters to 'Nagoya wards/neighborhoods' and specifying the 2025-2050 time frame, but it does not add syntax or format details beyond what the schema provides. Baseline of 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 it returns 'upcoming redevelopment, infrastructure, and population projections' for Nagoya wards/neighborhoods over 2025-2050, which is specific and informative. It does not explicitly name alternatives among siblings like get_population_outlook or forecast_land_price_trend, but the combination of scope and time range distinguishes it well enough for an agent to understand its purpose.

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 usage for future-plan-related queries ('upcoming redevelopment, infrastructure, and population projections') and mentions the time range, but it does not explicitly state when to prefer this tool over similar siblings or provide exclusion criteria. It relies on the agent inferring applicability from the content.

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, destructiveHint=false, and openWorldHint=false, so the description does not need to state the read-only nature. It adds useful context about the data source (NIPSSR) and the output years, which goes beyond annotations but does not delve into deeper behavioral aspects like rate limits or response format. No contradiction 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 short but somewhat redundant: the second English sentence ('projected population at 2030/2040/2050 with decline rate') essentially repeats the first, and the Japanese sentence is a direct translation. Not every sentence earns its place, though it is front-loaded with the core purpose.

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 low complexity (2 optional params, no output schema, no nested objects), the description covers the essential information: what data is returned, the time horizon, and the data source. It does not explain return format details, but for this simple lookup tool, the description is sufficiently 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?

Schema description coverage is 100%, meaning both parameters (area and prefecture) are thoroughly described in the schema. The description adds no additional semantic meaning beyond the schema, so it meets the baseline of 3 but does not exceed it.

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 specific verb ('Population outlook'/'projected population') and resource (population projections to 2050 with decline rate) based on NIPSSR data. It is unambiguous about what the tool does, though it does not explicitly differentiate from sibling tools like forecast_land_price_trend or simulate_aichi_future, which limits it to a 4 rather than a 5.

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 explicit guidance on when to use this tool versus alternatives, but the description implies usage for population projections to 2050. It does not mention exclusions or alternatives, making the usage context implicit rather than clearly stated.

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 destructiveHint=false, so the safety profile is covered. The description adds useful context about external data dependencies: e-Stat requires ESTAT_APP_ID and FRED uses a CSV. This is beyond the annotations, but it does not disclose what happens if the key is missing or how failures are handled. Adequate but not rich.

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, dense sentence with a bilingual summary, front-loading the core output. It is efficient and to the point, though the pipe-separated structure and bilingual text add slight noise. Overall, it is well-structured and 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 read-only tool with no output schema, the description covers the main returned data series and the optional external requirements. Missing are details about output format, fallback behavior if ESTAT_APP_ID is absent, or network dependencies. Given the tool aggregates multiple sources, a bit more context would help, but it is minimally adequate.

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 covers all parameters with clear descriptions (100% coverage), including the includeExternalSeries flag with the same ESTAT_APP_ID note. The description repeats some of this but adds no new meaning about parameters. Given high schema coverage, the baseline of 3 is appropriate; the description does not need to compensate.

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's purpose: providing a one-screen macro view of multiple real estate indicators (land price YoY, transaction counts, population decline, optional external series). It names specific data points, making it distinct from more specialized tools like get_population_outlook. However, it does not explicitly differentiate from all siblings, so it is clear but not maximally distinct.

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 'One-screen macro view' implies this is for a high-level overview scenario, and the optional external series section hints at when to include the flag. However, there is no explicit 'when to use vs. alternatives' statement, nor exclusions. Usage guidance remains implicit rather than explicit, so it meets the 'implied usage' level.

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 carry readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds scoping context (municipality grain, national-average comparison) but does not disclose return format or behavior when data is missing. Consistent with annotations, adds modest value 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.

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

Two compact bilingual sentences, key scoping info front-loaded, no filler. The bilingual mirror is slightly redundant but serves the JP-heavy domain, so it 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 read-only, fully-schema-documented, optional-parameter tool with no output schema, the description conveys the result contents (type breakdown + national comparison) sufficiently. An agent can call it correctly; only edge-case behavior is left unspecified.

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% — both parameters carry documented descriptions including the 'omit for full prefecture' nuance on area and the name/ISO-code handling on prefecture. The description adds no parameter syntax on top; 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?

States a specific verb+resource ('vacancy rate statistics by municipality') and enumerates the exact breakdown returned (total vacant, for-rent, for-sale, other) plus the national-average comparison. This clearly distinguishes it from statistics siblings like get_population_outlook and get_real_estate_macro_snapshot.

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 context of use is implied — an agent needing vacancy-rate data by municipality — but the description names no alternatives and gives no exclusions or conditions for choosing this tool over the many statistics/simulation siblings. Adequate but leaves routing to inference.

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 destructiveHint=false, so the safety profile is covered. The description adds value by explicitly listing the returned data fields (zone type, coverage ratio, floor area ratio, height limits), giving agents a concrete expectation of the output. It does not contradict 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 a single, compact sentence that front-loads the core action ('Look up zoning for an area') and immediately enumerates the key output fields. The bilingual suffix is redundant but not distracting. Every part earns its place; 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 straightforward lookup tool with three parameters (only one required), a read-only annotation, and no output schema, the description adequately covers the essential information: what the tool does and what it returns. The schema handles parameter details, and annotations handle safety. No critical information is missing for an agent to call it correctly.

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% — all three parameters (area, district, prefecture) are documented in the schema. The description adds no parameter-specific meaning beyond what the schema provides; it only mentions output fields. Since the schema fully explains the parameters, the baseline of 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 states a specific verb ('Look up'), a clear resource ('zoning for an area'), and enumerates the exact outputs (zone type, coverage ratio, floor area ratio, height limits). This clearly distinguishes it from sibling tools that analyze, assess, or simulate rather than fetch raw land-use data.

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 the tool is for obtaining zoning information, but it does not explicitly state when to use it versus alternatives, nor mention any exclusions or prerequisites. While the sibling list is dominated by analysis tools, no direct comparison is made. The intended use case is inferable but not stated.

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 destructiveHint=false, so the tool is clearly non-destructive. The description adds little beyond that, such as mentioning MCP Apps UI, which is a minor UI detail rather than a behavioral trait. No contradiction exists, but value added over annotations is minimal.

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 brief and front-loaded with the core action and modes. The Japanese translation is redundant but not harmful, and the whole is under 30 words. Slight waste in duplication prevents a 5.

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?

With an output schema present and the tool being a simple 'open' action, the description is somewhat adequate. However, it does not convey what the dashboard displays, how parameters interact, or what the user will see, leaving the agent to rely on the schema and output schema. Given seven parameters, a bit more context would help.

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 86%, with all parameters except propertyType having descriptions. The tool description adds no extra parameter context; it does not explain relationships, defaults, or the meaning of propertyType. Since the schema already does the heavy lifting, a baseline of 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 states a clear verb ('Open') and resource ('visualization dashboard'), and specifies two modes (2D map / PLATEAU 3D view). This is specific enough to distinguish from the data-analysis siblings, although it does not explicitly name which sibling it is not, so it stops short of a 5.

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 its purpose (use to open a dashboard) and lists modes, but provides no explicit guidance on when to choose 2D vs 3D, nor when not to use this tool or which alternative to pick. Basic context is present, exclusions are absent.

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 cover the safety profile (readOnlyHint:true, destructiveHint:false, openWorldHint:false), so the description only adds the return metrics. This is a minor addition, and the description does not disclose limitations beyond the 'up to 5 areas' constraint already in the schema. No contradiction 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?

One concise sentence (plus a bilingual translation) that front-loads the purpose and output. No fluff or repetition; every clause adds information.

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 tool with 5 parameters including an array of nested objects, the description provides only high-level output metrics. It lacks explanation of how optimization works or how parameters like optimizeFor affect the result, though the schema covers parameter semantics. Given the presence of annotations and no output schema, the description is adequate but could be richer.

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 80%, so most parameters have descriptions. The tool description adds minimal parameter insight: 'up to 5 areas' mirrors the maxItems constraint, and it does not explain optimizeFor, riskTolerance, or investmentHorizon. Baseline 3 is appropriate given the 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 verb 'Optimize' and the resource 'real estate investment portfolio' with a scope of 'up to 5 areas,' and lists the output metrics (expected return, risk score, Sharpe ratio). This distinguishes it from analytical siblings like compare_prefectures or cross_analyze_real_estate_market, 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?

No guidance is provided on when to use this tool versus the many siblings (e.g., compare_prefectures, scenario_what_if). It does not state the optimal use case or mention exclusions, leaving the agent to infer from the name and 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description's 'predict/算出' language is consistent with a read operation, so no contradiction exists. The description does add the useful '10 prefectures / 全10都道府県' scope constraint. However, it discloses nothing beyond that — no mention of input data sources, what the scores mean, output shape, or that only a subset of prefectures have full data (which the neighborhood schema description hints at). With read-only safety already covered by annotations, a 3 is fair: acceptable but light on 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.

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

At two short sentences with the core action front-loaded, it's tightly written and scannable. Half a point is lost to redundancy: the Japanese sentence is a near-verbatim translation of the English one (企業立地需要予測 ≈ 'predict corporate demand'), so roughly half the description repeats information already provided rather than adding distinct value for the consuming agent.

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 5 parameters, including an enum, and — critically — has no output schema, yet the description never explains what the call returns: score ranges, format, units, or how scores map to the three demand categories. For a scoring/prediction tool whose return contract is undocumented, this is a real gap. The geographic scope (10 prefectures) is there, but an agent cannot reason about the result without reading more; given the complexity and missing output schema, the description is noticeably incomplete.

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 80%, so the schema already documents most parameters (prefecture name formats, neighborhood example, propertyType enum, commute boolean). The description adds one genuinely useful semantic clue — the '10 prefectures' constraint on the valid geographic scope — but says nothing about the area/prefecture/neighborhood hierarchy or how includeCommuteAnalysis changes the result. The schema does the heavy lifting, so the description only marginally raises the baseline of 3.

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 ('Predict') and resource ('corporate demand') plus the three demand categories (manufacturing, office, retail) and scope (10 prefectures), which separates it from siblings like evaluate_store_location by telling the agent what domain it covers. It loses a point because 'corporate demand scores' is not operationalized — it never says what these scores represent or how they're expressed, and the bilingual repetition of the same two sentences adds no new meaning.

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. Siblings such as evaluate_store_location, get_population_outlook, compare_prefectures, and discover_opportunities plausibly overlap with corporate-demand prediction, yet the description offers no selection criteria, exclusions, or 'use X instead' routing. The agent is left to infer relevance from the name 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?

Annotations declare readOnlyHint=true and destructiveHint=false, and the description's rendering purpose is consistent with these — no contradiction. The description adds the ChatGPT-optimization context (compact layout for mobile views) and the markdown fallback behavior, which go beyond the annotations. However, it doesn't describe return format details, though the output schema likely covers this.

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?

Two sentences with zero waste, and the critical 'Always use this when...' routing guidance is front-loaded. The bilingual format is compact and efficient for a tool serving Japanese and English users.

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?

Complete for a rendering tool: contents are enumerated, the fallback behavior is disclosed, and usage directive is clear. With 5 parameters fully documented in the schema, an output schema present, and annotations covering safety, nothing critical 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?

Schema description coverage is 100%, so all 5 parameters are well-documented in the schema itself with Japanese/English descriptions plus enums for mode and intent. The tool description adds minimal parameter-level detail, but it does clarify the tool's overall purpose which helps interpret parameters like intent and compact in context. Baseline 3 is appropriate when schema carries the full load.

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 ('Render'), a specific artifact ('ChatGPT-optimized real estate visual summary'), and enumerates concrete contents (map, charts, recommended next actions, markdown fallback). It clearly distinguishes itself from sibling tools like open_dashboard or generate_area_report, which serve different purposes.

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?

Explicitly states 'Always use this when the user asks to show, visualize, compare, or continue in ChatGPT.' This provides unambiguous when-to-use guidance and implies it's the rendering layer on top of analysis tools, helping an agent route correctly among many sibling 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile, so the bar is lower. The description adds the cross-ward scan behavior ('scan all 16 Nagoya wards'), which is useful contextual information beyond the annotations. It does not disclose return format or pagination limits, but annotation coverage makes 3 appropriate.

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 at two sentences, with the English purpose front-loaded and the Japanese translation after. The bilingual repetition adds minor redundancy but no waste; the core scoping information is delivered efficiently.

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 ranking tool with all 4 parameters optional and annotated as read-only, the description covers scope and purpose adequately. However, it omits details about what constitutes the yield computation, what data types it relies on, and the output shape (no output schema exists). Since an agent could invoke it correctly with defaults, but gets no information about the result format, 3 is fair.

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 75%, and the schema already documents all four parameters (limit, floorArea, buildingAge, propertyType) with descriptions and defaults. The description adds the yield-ranking context that connects floorArea/buildingAge to the yield computation, but provides no parameter-specific syntax beyond the schema. Baseline 3 is correct 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 states a specific verb+resource: scan all 16 Nagoya wards and rank neighborhoods by renovation yield. It clearly distinguishes from analysis tools like analyze_renovation_yield by establishing a cross-ward scanning scope. However, it doesn't explicitly name sibling differentiators, so a 5 isn't warranted.

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 siblings such as analyze_renovation_yield, discover_opportunities, or detect_arbitrage_signals. The description implies a use case (ranking across all wards) but never states exclusions or alternatives, leaving the agent to infer when this is the right choice.

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 destructiveHint=false, so the description does not need to restate safety. It adds significant behavioral context by specifying the evaluation axes and the output structure (decision, red flags, negotiation points, clauses), which goes beyond the annotations. It does not contradict any annotation.

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 bilingual (English/Japanese) which adds some length, but both versions are concise and front-load the core purpose before listing outputs. It packs a lot of information into two sentences without redundant filler, appropriate for a tool with 25 parameters.

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?

With a complex schema (25 parameters, nested objects) and an output schema present, the description provides a solid overview of what the tool evaluates and returns. It does not explain how to fill in parameters, but the schema covers that. It also mentions the output_mode parameter (compact/detailed), which is useful context. Minor gap: no mention of data prerequisites or assumptions, but not critical given the schema richness.

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 all 25 parameters. The tool description references some parameters indirectly (e.g., 'asking price vs 公示地価/路線価/取引相場' maps to kojiPricePerSqm, rosenkaPricePerSqm, transactionMedianPerSqm) but does not add new meaning beyond what the schema provides. This meets the baseline for 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 states a specific verb ('review') and resource ('purchase recommendation') and details the evaluation criteria (asking price vs 公示地価/路線価/取引相場, yield, risk, future potential, contract terms) and outputs (5-axis scores, decision, red flags, negotiation points, recommended clauses). This clearly distinguishes it from narrower sibling tools like assess_property_risk or assess_contract_risk, which focus on single risk dimensions.

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 it is for a holistic purchase decision review ('Real estate purchase review for executives') but does not explicitly state when to use it instead of a sibling tool such as assess_property_risk or composite_value_score. It gives context but no exclusions or alternative routing, leaving the agent to infer usage from the 'purchase review' wording.

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 destructiveHint=false, and the description's 'simulate impact' aligns with a non-destructive read operation. The description adds useful context beyond annotations by specifying the scope (10 prefectures) and scenario types. No contradictions 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?

The description is two short sentences with a bilingual summary, front-loading the core purpose without any unnecessary words. It is concise and well-structured.

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 read-only simulation tool with a fairly rich schema, the description covers purpose and scope (10 prefectures, scenario types). It doesn't describe the output format, but that's acceptable given no output schema and the read-only nature mentioned in annotations. The agent has enough context to correctly select and invoke the tool.

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 covers 67% of parameters with descriptions (city, scale, scenario, prefecture), and the description adds context by naming example scenarios that map to the scenario enum (e.g., new stations, commercial facilities). However, it does not explain parameters like scale, horizon, or includeMarkdown, so the added meaning is modest. Given the moderate schema coverage, a middle score 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 simulates the impact of specific scenarios (new stations, commercial facilities, population changes) on land prices and investment scores, with a defined scope of 10 prefectures. It is specific and not a tautology, but it does not explicitly distinguish itself from sibling simulation tools like simulate_aichi_future or simulate_landscape_impact.

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 a clear context: use this tool when you need to simulate what-if impacts on land prices and investment scores. However, it does not mention exclusions or contrast with alternatives, so while the context is clear, there are no explicit routing instructions.

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 mark the tool as readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds that it returns a candidate list and is 'ChatGPT-compatible,' implying natural language acceptance. It does not disclose result limits, pagination, or other behaviors, but given the annotation coverage, this is acceptable. No contradiction 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 compact—two short sentences, with the English and Japanese versions. It front-loads the core purpose. The phrase 'ChatGPT-compatible' is somewhat superfluous but not harmful. No unnecessary 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 single-parameter search tool with read-only annotations, the description is minimally complete: it states what it searches and that it returns a candidate list. The absence of an output schema is mitigated by the clear intention, but the agent lacks detail on result structure or how to interpret candidates. Given the tool's simplicity, this is acceptable but not thorough.

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 covers the only parameter 'query' with 100% coverage, including a detailed description with examples. The tool description adds no parameter-specific information beyond what the schema already provides. Baseline of 3 is appropriate when the schema fully documents the parameter.

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 identifies the verb (Search) and resource (real estate data catalog) and lists the covered entity types (areas, tools, data sources). It implicitly distinguishes itself from search_area_candidates by covering more than areas, though it does not explicitly name the sibling. The purpose is unambiguous.

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 explicit guidance is given on when to use this tool versus alternatives like search_area_candidates or the analysis tools. The phrase 'ChatGPT-compatible' is vague and does not clarify contextual fit. The description neither states exclusions nor recommends conditions for use, leaving the agent to infer.

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 convey readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds useful behavioral context beyond annotations: it specifies support for hiragana input, which is not obvious from the schema and indicates a specific matching behavior. It does not detail rate limits, error handling, or return format, but given annotations cover the read-only nature, the description contributes meaningful extra behavioral 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?

The description is succinct: two sentences separated by a delimiter, with the primary English statement followed by a Japanese translation. The core purpose is front-loaded, and every clause serves a purpose—stating function, scope, and an important feature. There is no fluff or redundancy, making it highly efficient.

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 with three optional parameters fully documented in the schema, the description is largely complete. It specifies the input behavior and the type of output ('candidates'). While it does not explain the return structure or pagination, the absence of an output schema and the simplicity of the task lower the need for such detail. The description covers the essential context for correct usage.

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 each parameter (limit, query, prefecture) is already documented. The description adds a minor hint about query semantics by mentioning 'partial text' and hiragana support, but it does not add deeper meaning beyond the schema. The limit and prefecture parameters are not elaborated in the description, but since the schema covers them, the description meets the expected 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 clearly states the tool's function: 'Search municipality name candidates by partial text.' The verb is specific ('Search'), the resource is specific ('municipality name candidates'), and the mode ('by partial text') is explicit. The additional note 'Supports hiragana' further clarifies the search behavior. This distinguishes it from sibling tools like the generic 'search' and others focused on analysis rather than lookup.

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 (when you need to find municipality names from partial text) but does not explicitly state when not to use it or mention alternatives. For instance, the sibling 'search' might be a more general alternative, but the description does not address differentiation. There is no guidance on prerequisites or fallback options, so it offers only an implied 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds context beyond annotations by specifying the exact simulation inputs (the four named projects) and the output format (Markdown report), which is useful behavioral information. No contradiction with annotations is present.

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, with two sentences (one English, one Japanese translation). It front-loads the core purpose and enumerates the key drivers. The bilingual duplication is slightly wasteful but not excessive. It earns a 4 for efficiency, losing one point for the redundant translation that adds no new information for an English-speaking agent.

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 read-only simulation tool with 4 parameters (1 required) and no output schema, the description covers the essential context: what it simulates (four named projects), and what it returns (a Markdown report). The schema handles parameter definitions, and annotations cover safety. The description does not detail the report's structure, but given the tool's simplicity and lack of an output schema, this is acceptable. It is sufficiently complete for an agent to call it correctly.

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 75% (city, horizon, scenarios each have descriptions; includeMarkdown lacks one). The description does not add substantial parameter semantics beyond what the schema already provides; it merely restates the scenario names in prose (e.g., 'Linear Chuo Shinkansen' corresponds to the 'linear_chuo' enum). The includeMarkdown parameter is self-explanatory from its name, so the description need not elaborate. Since schema coverage is high, a baseline of 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 states a specific verb and resource: 'Aichi future value simulator' that models the impact of four named projects (Linear Chuo Shinkansen, Centrair 2nd runway, Toyota EV investment, Expo legacy) on land prices, producing a Markdown report. This is clear and specific. However, it does not explicitly differentiate from sibling tools like 'simulate_landscape_impact' or 'scenario_what_if', which could overlap in purpose.

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 its siblings. It does not mention alternatives, preconditions, or situations where another tool would be more appropriate. An agent would have to infer the use case solely from the project names, which is insufficient given the large set of analysis tools available.

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 destructiveHint=false, so the safety profile is covered. The description adds the data sources (PLATEAU, SunCalc) and that it analyzes surrounding buildings, but doesn't disclose return format, performance characteristics, or regional limitations. With annotations covering safety, a 3 is appropriate.

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 and front-loaded with the main purpose in English, followed by a Japanese duplicate. The duplication adds length but serves bilingual users; it's efficient overall and lacks filler.

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?

With 7 parameters and no output schema, the description should explain what the tool returns (e.g., whether it outputs a report, visual, or data) and any limitations (e.g., Japan-specific, prefecture default). It does not mention includeMarkdown or output format, nor when to prefer it over sibling tools. This leaves critical gaps for correct invocation.

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 86%, so the schema documents most parameters adequately. The description adds no parameter-specific semantics (e.g., meaning of radiusM, dateTime formatting), but the high coverage means the schema carries the burden. Baseline 3 is justified.

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 simulates sunlight/shadow impact using PLATEAU 3D buildings and SunCalc, with a specific verb ('simulate') and resource (landscape impact). It distinguishes itself from obvious siblings like simulate_aichi_future and simulate_leveraged_cashflow by focusing on geography-based light analysis, though it doesn't 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?

The description provides no guidance on when to use this tool versus alternatives, no prerequisites, and no exclusions. It simply states what it does, leaving the agent to infer usage context on its own.

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 destructiveHint=false, covering the safety profile. The description adds value beyond that by enumerating the computed metrics (NOI, debt service, after-tax cash flow, DSCR, IRR, equity multiple, sensitivity), which helps the agent understand the output composition. It does not mention limitations or default behaviors for omitted optional parameters, but those are largely covered by schema defaults. No contradiction 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 two concise sentences (English and Japanese translation) that front-load the core purpose and output metrics. Every phrase carries information – no filler. It efficiently summarizes a complex tool without redundancy, which is appropriate for the parameter count and nesting.

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 complex (17 params, nested objects, output schema present) and the description captures the essential function and outputs. Since an output schema exists, return values are documented there, so the description needn't detail them. It does not mention the output_mode parameter, but the schema covers it. Overall, the description is sufficient for an agent to call the tool correctly with the schema's support.

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 every parameter is already documented with descriptions and defaults. The tool description only restates a handful of inputs (interest rate, LTV, rent, vacancy, etc.) without adding new meaning or clarifying relationships beyond what the schema provides. Per rubric, baseline 3 is appropriate when the schema fully covers parameter semantics.

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's function: a leveraged 10-year real estate pro-forma. It specifies the resource (real estate cash flow) and the specific verb (simulate/試算), and lists distinct outputs (NOI, debt service, DSCR, IRR, equity multiple, sensitivity) that set it apart from sibling tools like simulate_aichi_future or simulate_landscape_impact. The name and title reinforce the distinct leveraged cash-flow focus.

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 clear context (when to use: for leveraged cash flow analysis with debt and tax assumptions) but does not explicitly mention alternatives or exclusions. Sibling names indicate other simulation tools exist, but the description does not say 'use this instead of X when...' – leaving the agent to infer from the name and purpose. This is adequate but lacks explicit routing guidance.

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