Japan Real Estate Intel

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

Annotations already declare the tool read-only and non-destructive, so the safety profile is clear. The description adds some behavioral context by listing the outputs (acquisition cost, renovation cost, rent, yields) and noting 'future plan upside', but it does not disclose details like how the acquisition price is estimated when omitted or what the return format is. 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 extremely concise: one English sentence and one Japanese translation, front-loaded with the core purpose. Every word contributes to explaining what the tool does. 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?

For a read-only analysis tool with six parameters and no output schema, the description covers the main purpose, geographic scope, and included outputs. However, it does not mention the return format, data sources, or how the optional acquisition price is handled (though the schema covers that). It is fairly complete for the tool's complexity, but could give a bit more context on the output structure.

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 provides 100% description coverage for all six parameters, so the baseline is 3. The description does not add extra meaning to the parameters; it merely lists the outputs that would be calculated from them. It does not clarify parameter formats, units, or relationships beyond what the schema already provides.

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 with specific verbs ('calculate') and resources (acquisition cost, renovation cost, expected rent, gross/net yield) for Nagoya neighborhoods. It distinguishes itself from sibling tools like 'recommend_renovation_targets' by focusing on quantitative yield calculation rather than recommendation.

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 use case (analyzing renovation yield for specific property conditions in Nagoya), but it does not explicitly state when to use this tool versus alternatives or mention any exclusions. The context is clear but there is no explicit guidance on choosing between this and similar analysis 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?

With annotations declaring readOnlyHint=true and destructiveHint=false, the description adds useful context about what is analyzed (financing, inspection, future value terms) and what is returned (risk score, deal-breakers). It does not contradict the annotations and provides sufficient transparency for a read-only analysis tool.

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), front-loaded with the core purpose and output. There is no fluff or repetition of structured fields, making it highly concise while still conveying essential 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 a nested object and no output schema, the description covers the main inputs, what is examined, and the output format (risk score, deal-breakers). It could mention how ward/chochou factor into the assessment or the risk score scale, but the current description is sufficient for basic 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 coverage is 100%, but the schema descriptions are minimal and in Japanese. The tool description adds semantic value by specifying what proposedTerms should contain (e.g., financing contingency, inspection, future value terms), going beyond the schema's generic 'JSON format' label. This helps the agent construct meaningful input.

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: analyzing proposed contract clauses (financing contingency, inspection, future value terms) and returning a risk score with deal-breakers. This specific verb+resource differentiates it from sibling tools like assess_property_risk, which focuses on property risk rather than contract terms.

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 intended use case—when you need to evaluate risk in proposed contract clauses—but does not explicitly state when not to use it or mention alternative tools. The context is clear enough to guide selection, though exclusions or alternatives would make it more 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 safe read-only nature is covered. The description adds useful context about the scope (10 prefectures, 3 axes) but does not disclose what the output looks like or behavior for prefectures outside the 10. Given annotations, 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 lines, front-loaded with the core purpose, and includes a bilingual version. No wasted words; it efficiently communicates scope and assessment dimensions. The repetition between English and Japanese is acceptable for international user support.

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 6 parameters, no output schema, and the description does not explain the return value (e.g., a score, breakdown, or comparison). The scope of 10 prefectures and 3 axes is clear, but missing details about output format and how optional parameters are used make it incomplete for a tool of this complexity.

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 has 67% description coverage, so some parameters (area, address, prefecture, neighborhood) have basic descriptions. The description mentions the 3 axes which map to relevant inputs (e.g., childAge for education), but it does not detail how parameters affect the assessment. It adds some meaning beyond the schema but not substantial.

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: assessing family-friendliness across education, safety, and healthcare axes, with a scope of 10 prefectures. It uses a specific verb ('assess') and identifies the resource and axes. However, it does not explicitly differentiate from sibling tools like compare_prefectures or generate_area_report, so it is clear but not fully distinguishing.

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 is clear: this tool is for evaluating residential suitability for families across the 3 specified axes and 10 prefectures. No exclusions or alternatives are mentioned, but the specialized purpose implies when to use it (when a family-friendliness score is needed). This meets the 'clear context, no exclusions' 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 declare readOnlyHint=true and destructiveHint=false. The description adds that scoring is integrated across 10 prefectures, which is useful behavioral context. It does not contradict any annotations and provides a bit more than the bare 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 two short sentences in English and Japanese, front-loaded with the verb and purpose. It is concise without any fluff, and the bilingual version adds clarity for a broader audience.

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 risk scoring tool, the description captures purpose, covered risk types, and geographic scope. It hints at output via 'integrated scoring' but doesn't detail the return format. Given the tool's moderate complexity and lack of output schema, this is adequate but not exhaustive.

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 descriptions cover address, prefecture, and neighborhood. The description reinforces riskTypes by listing flood, landslide, and earthquake, and alludes to prefecture coverage. However, it does not explain the latlng parameter or add detail beyond the schema's 60% 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 tool assesses property disaster risk, listing specific risk types (flood, landslide, earthquake) and integrated scoring. This distinguishes it from sibling tools like assess_contract_risk or assess_family_friendly_score.

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 on what the tool covers (flood, landslide, earthquake, 10 prefectures), making the use case obvious. It does not explicitly mention alternatives or exclusions, but the context is unambiguous for an agent to select it over siblings.

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 'Markdown output,' which is a behavioral detail, but it may conflict with the schema's exportFormat default of 'json', creating ambiguity. No mention of xlsx base64 behavior or other edge cases.

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 and front-loaded, with the first sentence stating purpose. The Japanese translation is redundant but not excessive. However, the 'Markdown output' phrase is not fully accurate given the schema's format options, so it could be tighter.

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 only simple annotations, the description should provide more context about return values, format selection, and edge cases (e.g., xlsx base64, neighborhood support). It only covers the high-level purpose and a single output format mention, leaving much 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 57% (4 of 7 parameters described). The description mentions comparison dimensions (land price, population, risk, investment score), but 'population' is not in the metrics enum, which could confuse. It does not clarify required prefectures, max 5, or the various format options despite coverage being moderate.

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 action ('Compare'), the resource ('prefectures'), and the scope (up to 5, with specific dimensions: land price, population, risk, investment score ranking). This is specific and distinguishes it from siblings like cross_analyze_real_estate_market, which covers broader market cross-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 implies when to use the tool (comparing prefectures on investment-relevant metrics) but provides no explicit guidance on when not to use it or how it differs from alternatives. No exclusions or alternative tool references are given, which would help an agent select it correctly.

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 safety is covered. The description adds the output components (radar, tier, peer comparison, AI narrative) as behavioral context, but does not disclose prerequisites such as the Gemini API key for narrative generation or any data requirements.

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 concise sentences, front-loaded with the core purpose and outputs, followed by a Japanese translation. No redundant content.

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

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

Given the tool's complexity (7 parameters, nested weights, multiple output modes), the description still communicates the core function and key outputs, and the rich schema fills in parameter details. However, it omits usage context and the prerequisite for AI narrative (Gemini API key), which is disclosed only in 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 100%, so parameters are well-documented in the schema. The description enumerates the five axes, which match the weights object fields, but adds no additional semantic detail beyond the schema.

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

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

The description uses a specific verb ('fuse') and identifies the resource (5 axes: land price, education, transport, future plans, risk) and the result (single 0-100 score with radar, tier, peer comparison, AI narrative). This clearly differentiates from sibling tools that focus on individual dimensions or other composite scores.

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 use when an overall area value score is needed, but provides no explicit when-to-use or when-not-to-use guidance and does not mention alternative tools. Sibling tools like assess_family_friendly_score or assess_property_risk could overlap, but no exclusion is given.

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?

The description adds a 10-prefecture limitation, which is a useful behavioral constraint. However, it does not disclose output format, return structure, or any latency/processing traits, and relies on the readOnlyHint annotation to convey safety. No contradiction exists.

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 core purpose, but the Japanese sentence is a direct translation that adds no new information. Still, the overall length is appropriate and does not contain unnecessary verbosity beyond the bilingual duplication.

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 (14 parameters, no output schema), the description is under-specified. It lacks any indication of the return format, how the cross-analysis is presented, or how to select between compact and detailed modes. The description would be inadequate for an agent to fully understand the tool's capability without examining 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?

With 79% schema description coverage, the schema already documents most parameters. The description adds a high-level narrative tying parameters together (e.g., foot traffic, education, corporate presence correspond to includeHumanFlow, includeEducation, includeCorporate), but it does not introduce new parameter-level details beyond the schema.

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

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

The description clearly states the tool's function with a specific verb ('cross-analyze') and a defined resource (real estate market) with explicit dimensions (land price trends, investment score, foot traffic, education, corporate presence). It also notes the 10-prefecture scope, distinguishing it from sibling tools like compare_prefectures or forecast_land_price_trend.

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

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

The description provides no explicit guidance on when to use this tool instead of alternatives like generate_area_report or get_real_estate_macro_snapshot. It does not mention exclusions or alternative scenarios, leaving the agent to infer usage from the purpose alone.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds the core behavior (cross-checking three price metrics) and signal outputs, but does not disclose additional traits like data freshness, potential API-key requirements for live fetch (only in schema), or response structure beyond the output schema. It provides some added context but not rich behavioral detail.

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

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

The description is a compact two-sentence structure, front-loaded with the primary verb and resource. The Japanese sentence repeats the English content, which is arguably redundant but serves localization; it is still concise and does not waste significant space, though it could be trimmed to a single sentence.

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

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

The description adequately explains the tool's purpose and the types of signals it detects, which is sufficient for a read-only scanner with a rich output schema and fully documented parameters. It does not explain how the triangulation works or return-value details, but those are either covered by the output schema or not essential for 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 100%, so the schema fully documents all five parameters, including defaults, enums, and bilingual descriptions. The tool description adds no parameter-specific meaning beyond what the schema already provides, justifying 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 clearly states a specific action ('cross-checks') and resource (three price datasets: rosenka, koji, tx) to detect specific signal types (discount buys, inheritance-tax edges, overheated markets). This distinguishes it from generic scanning tools and matches the title's arbitrage 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?

Clear context is given: the tool is for detecting price arbitrage signals from three valuation sources. It implies when to use (when seeking discount, inheritance, or overheating insights) but does not explicitly name alternatives or exclusions among the many sibling tools, so it stops short of a 5.

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

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 that results are 'hypothesis cards with multi-source scoring,' which gives some output context, but it does not disclose potential external API dependencies (mentioned only in the schema), data freshness, or scoring methodology. 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 English description is concise and front-loaded with the tool's core purpose in two sentences. The bilingual duplication adds length but is not excessive. There is no filler or irrelevant content.

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

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

For a tool with 10 parameters and many sibling tools, the description gives the essential purpose and output but lacks usage guidance and behavioral specifics. It does not clarify what 'multi-source scoring' means or how this tool differs from alternatives. The output schema exists, but the description alone is only 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 schema description coverage is 70%, so most parameters are already documented. The description only indirectly references goal and prefecture, adding no extra meaning for parameters like horizon, riskTolerance, or includeMarkdown. It provides minimal compensation for the few undocumented parameters.

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 ('scan'), the resource ('a prefecture'), and the output ('hypothesis cards with multi-source scoring'). It also lists the accepted goal types, making the tool's purpose specific. However, it does not explicitly distinguish itself from sibling tools like search_area_candidates or detect_arbitrage_signals.

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 or when-not-to-use guidance is provided. The description only implies usage for prefecture-level opportunity discovery, and no alternative tools are named even though many siblings exist. This leaves the agent without clarity on how to choose between discover_opportunities and similar 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, so the safety profile is clear. The description adds that the tool outputs Markdown and covers specific data topics, but it does not disclose limitations (e.g., unsupported prefectures for neighborhood) or clarify the default output format versus exportFormat parameter.

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 main purpose front-loaded in both English and Japanese. The bilingual repetition is somewhat redundant but serves a clear audience. No filler or unnecessary detail, though a structured breakdown could improve scannability.

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 and no output schema. The description provides a high-level view but misses critical details such as the exportFormat default (json vs stated markdown), support limitations for neighborhood data, and potential fallback behavior. While adequate, it leaves ambiguity for an agent deciding on 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 80%, so most parameters are self-explanatory. The description adds related content categories (foot traffic, commercial, education) but does not explicitly map them to the 'focus' parameter or provide syntax beyond what the schema already includes. 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 performs a drill-down local analysis at block/neighborhood level, specifying content areas (foot traffic, commercial, education) and output format (Markdown). This distinguishes it from broader area reports or macro tools, though it does not explicitly name sibling tools.

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

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

No explicit guidance is provided on when to use this tool versus alternatives like generate_area_report or get_chochou_profile. The description implies use for detailed local analysis but does not state exclusions or contrast with other tools, leaving selection ambiguous.

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?

The description adds that a score is calculated based on foot traffic, transport, and competitor distribution, and mentions the 10-prefecture constraint. It does not fully disclose which prefectures, output format, or effects of customWeights, but annotations already cover readOnlyHint and destructiveHint, so no contradiction exists.

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 Japanese, front-loaded with the core purpose. There is minor bilingual repetition, but it serves multi-language clarity and does not waste space.

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, nested objects, no output schema, and a vague prefecture scope, the description is insufficiently complete. It does not explain the scoring scale, which prefectures are covered, or how results are returned, leaving significant ambiguity for an agent.

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 carries most parameter meaning. The description mentions conceptual factors (foot traffic, transport, competitor distribution) but adds little beyond the schema for specific parameters like prefecture, neighborhood, customWeights, or includeMarkdown.

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 evaluates store location suitability and lists the key factors (foot traffic, transport, competitor distribution). It does not explicitly differentiate from sibling tools, but the verb and resource are specific and understandable.

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 useful constraint ('10 prefectures' / '全10都道府県'), indicating scope. However, it does not list which prefectures, nor does it contrast with alternatives like search_area_candidates or compare_prefectures. The guidance is minimal but not 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 mark it as read-only and non-destructive. The description adds that the ID comes from search results and that returns are in Markdown, but it doesn't disclose error behavior, pagination, or size limitations. This basic context is helpful 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 compact with two parallel sentences (English and Japanese). It front-loads the action and return format, though the Japanese translation is redundant for an English-only agent, making it slightly less efficient than it could be.

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 fetch tool, the description covers purpose, source of ID, and return format. It lacks details about errors or edge cases, but the schema and annotations cover essentials, making it adequately complete for this simplicity.

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 fully describes the single 'id' parameter (100% coverage), including example format. The tool description only echoes 'from search results' without adding new semantic details beyond what the schema already provides.

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 fetches a full document by ID from search results, specifying the content type (area analysis, forecasts, summaries) and format (Markdown). This distinguishes it from search and other analysis siblings that focus on different aspects.

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

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

It gives clear context that the tool is used after obtaining an ID from search results, implying a search-then-fetch workflow. However, it doesn't explicitly name alternatives or state when not to use it, so it stops short of full guidance.

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 known to be safe. The description adds context by disclosing the methods used (linear regression, moving average), the specific outputs (CAGR, confidence interval, investment signal), and the coverage scope (10 prefectures). This goes beyond the annotations, though it does not mention data sources or limits within those prefectures.

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 core purpose. It includes both English and Japanese text, which is a slight redundancy for an AI agent but still compact. Every sentence adds some value, with the Japanese translation being the only potentially unnecessary part, preventing a perfect 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?

The tool has 7 parameters and no output schema, so the description must convey return expectations. It mentions key outputs but leaves gaps: which 10 prefectures are covered, what the investment signal (buy/hold/caution) means, and how outputs are formatted. The annotations and schema cover safety and parameters, but the description does not fully compensate for the missing output schema.

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

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

Schema description coverage is 86%, so parameters are well-documented in the schema. The description does not add extra meaning to parameters; it only mentions the method types and outputs, which are already covered by the schema enums and descriptions. The includeMarkdown parameter lacks a description but is a simple boolean, and the description does not clarify it further.

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 with a specific verb ('Forecast'), the resource ('land price trends'), the methods ('linear regression and moving average'), and the outputs ('CAGR, confidence interval, investment signal'). It also specifies the scope ('10 prefectures'), making it distinct from sibling tools that assess risk or compare prefectures.

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 forecasting land prices but provides no explicit guidance on when to use this tool versus alternatives. It does not name any sibling tools or specify exclusions. The '10 prefectures' scope is a constraint, but there is no clear when-to-use/when-not-to-use instruction.

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?

The description does not contradict the readOnlyHint and destructiveHint annotations. It adds useful context such as the 10-prefecture limitation and branding support, but does not disclose details about PDF base64 output or whether it requires data availability. Given annotations already cover the safety profile, this is acceptable.

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 English sentences plus a Japanese translation. It front-loads the core action and scope, but the bilingual repetition adds some redundancy while still being 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 13 parameters and no output schema, the description is surprisingly sparse, but the schema provides descriptions for 77% of parameters including the PDF base64 behavior. Still, the required 'area' and 'purpose' fields are undocumented, and the description gives no guidance on how to use them, making the tool harder to invoke 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 77%, and the description does not elaborate on parameters like 'area' and 'purpose' beyond the schema. The high-level mention of branding hints at agentName/companyName/logo parameters, but no specific parameter semantics are added. Required parameters area and purpose have no descriptions in either schema or tool description, leaving ambiguity.

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 generates a comprehensive area report in Markdown/PDF with branding support, and specifies a scope of 10 prefectures. This distinct verb-resource pairing (generate report) differentiates it from sibling analysis tools that don't produce such reports.

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 siblings like analyze_renovation_yield or cross_analyze_real_estate_market. Usage is implied by the word 'Generate', but alternatives are not mentioned or excluded.

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 clear. The description adds behavioral context about output format (Markdown + branded PDF) and content (risk matrix, anchors, clauses), but it does not disclose details like data sources beyond 'neighborhood/property data', processing time, or potential errors. This is sufficient 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 extremely concise: two sentences covering purpose, inputs (neighborhood/property data), outputs (risk matrix, anchors, clauses), and output format. The bilingual Japanese translation adds accessibility. No 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?

The description explains the core outputs and output format, which is substantial for a tool with no output schema. It does not detail the structure of the generated PDF or the exact algorithm, but the parameter schema is complete and the tool's function is clear. Given the moderate complexity (7 params), this is adequately complete, though missing explicit mention of how the package is delivered or any prerequisites.

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?

All 7 parameters are fully described in the schema (100% coverage), so the schema carries the semantic burden. The description does not add extra meaning to parameters; it only mentions outputs derived from them. 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 a specific verb ('generate') and resource ('contract support package'), listing concrete outputs: risk matrix, price negotiation anchors, and recommended clauses. It distinguishes itself from sibling tools like 'assess_contract_risk' by emphasizing generation of a package rather than assessment, and from 'review_purchase_recommendation' by focusing on contract support specifically.

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 a user needs a contract support package with risk matrix, negotiation anchors, and recommended clauses. However, it does not explicitly state when to use this tool over alternatives like 'assess_contract_risk' or 'review_purchase_recommendation', nor does it provide exclusions or conditions.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds context about the returned data categories and that they are 'current,' but it does not disclose pagination, output formatting, or how missing data is handled. This is acceptable for a simple read-only tool but not particularly 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, one English and one Japanese, efficiently front-loading the purpose. No filler words; all content is directly useful.

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 simple tool (3 params, no output schema), the description adequately covers what is returned and for which area. It does not explicitly state that omitting chochou returns ward-level data, but that is available in the schema. The description is reasonably complete for an agent to understand the tool's purpose and basic output.

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%: all three parameters (ward, chochou, output_mode) have descriptions. The description does not add parameter-specific detail beyond the schema; it mentions metric types but that is more about output than parameter semantics. Baselines at 3 as per rubric.

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 tool as providing a neighborhood profile with specific current metrics (land price, population, households, ongoing plans) for Nagoya wards/neighborhoods. This specific resource and scope distinctively sets it apart from sibling tools like get_vacancy_stats or get_zoning_info.

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 retrieving current local data for Nagoya, but it does not explicitly state when to use this tool over alternatives or provide exclusion criteria. The scope is clear, but no sibling tool comparisons or when-not-to-use guidance are given.

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 adds useful context about the time range and content categories. However, it does not disclose output format, pagination, or behavior for missing or invalid ward/neighborhood values, so behavioral detail remains limited.

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

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

The description is compact: two sentences (one English, one Japanese) with no filler. The front-loaded noun phrase 'Future timeline' immediately conveys the tool's purpose, and the bilingual format is reasonable for the expected audience.

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 read-only tool with two parameters and no output schema, the description adequately explains what is returned and the time scope. It could be slightly more explicit about the structure of the timeline (e.g., events with years), but overall it is sufficient for a tool of this complexity.

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 parameters. The description reinforces that these refer to Nagoya wards/neighborhoods, but it does not add meaningful detail beyond the schema, such as how chochou omission affects results or expected input formats.

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 specifies the tool's function: returning an annual timeline of upcoming redevelopment, infrastructure, and population projections for Nagoya wards/neighborhoods from 2025-2050. This goes beyond the tool name and distinguishes it from sibling tools that focus on current stats or land price forecasts.

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 use when future planning information for Nagoya areas is needed, but it does not explicitly state when to use this versus overlapping siblings like get_population_outlook or forecast_land_price_trend. No alternatives or exclusions are mentioned.

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 safety is covered. The description adds useful context about data source (NIPSSR) and specific forecast years, but does not disclose limitations like computation method of decline rate or update frequency. 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 sentences, bilingual, and front-loaded with the essential output details. There is no redundant text or repetition of schema 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?

Given the tool's simplicity (two optional params, no output schema), the description adequately covers the main return values (2030/2040/2050 population, decline rate) and data source. It falls slightly short on explaining the meaning of 'decline rate' or the response format, but overall is sufficient for its complexity.

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% with both parameters described (area as optional target city, prefecture with default). The description does not add parameter-specific meaning beyond the schema, but it provides general context about the data source. Baseline 3 is appropriate given full 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 identifies the tool as a population outlook to 2050, specifying projected population at 2030/2040/2050 and decline rate, based on NIPSSR data. This is a specific verb-noun combination that distinguishes it from sibling tools like simulate_aichi_future or forecast_land_price_trend.

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 obtaining population projections but does not explicitly mention when to use this tool versus alternatives, nor does it provide exclusions or context for selection among sibling tools. Usage guidance is limited to what the tool returns.

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 establish read-only, non-destructive behavior (readOnlyHint true, destructiveHint false). The description adds valuable context that includeExternalSeries triggers e-Stat (requiring ESTAT_APP_ID) and FRED CSV fetches, and that population decline is projected to 2050. 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 and front-loaded with 'One-screen macro view,' efficiently listing the core metrics in one sentence. However, the second sentence is a verbatim Japanese translation, which adds length for English-only readers, though it may aid bilingual users. Overall 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?

With no output schema, the description explains the output as a one-screen macro view and enumerates the included data series, plus optional external data dependencies. It is sufficient for a read-only snapshot tool, though it does not detail the exact visualization format or how missing ESTAT_APP_ID is handled, which is a minor gap.

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 baseline is 3. The description adds the ESTAT_APP_ID dependency tied to includeExternalSeries, but does not add meaningful nuance for 'area' or 'prefecture' beyond the schema's existing descriptions. It provides minimal additional 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 opens with 'One-screen macro view' and names the specific resource: land price YoY, transaction counts, population decline to 2050. It clearly distinguishes the tool from sibling analysis tools by positioning it as a single consolidated macro snapshot, with a specific verb 'get' and resource '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 description clearly implies use for a quick, consolidated overview of macro real estate indicators, and mentions optional external series (e-Stat, FRED). However, it does not explicitly state when to prefer this tool over siblings like get_population_outlook or forecast_land_price_trend, nor does it list exclusions.

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 signal readOnlyHint=true and destructiveHint=false, and the description adds behavioral context by specifying the breakdown by vacancy type and the comparison to national average. This sets clear expectations for the output without contradicting 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 a single front-loaded sentence with both English and Japanese versions. The bilingual repetition is slightly redundant but serves the intended audience and keeps the structure compact. Every major point is covered without excessive detail.

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

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

There is no output schema, so the description carries the burden of explaining return values. It lists the vacancy types (total, for-rent, for-sale, other) and the national comparison, which covers the core output. It does not mention data source or units, but for a simple read-only stats tool this is reasonably 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 detailed descriptions for 'area' (target city, omit for full prefecture) and 'prefecture' (supports Japanese, English, ISO 3166-2). The description text does not add parameter-specific semantics beyond the schema, but the baseline of 3 is appropriate given full 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 specifies the exact resource (vacancy rate statistics), the scope (by municipality), and the output dimensions (total vacant, for-rent, for-sale, other, compared to national average). This clearly distinguishes it from sibling tools like compare_prefectures or 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 description implies usage for municipality-level vacancy breakdowns, but it does not explicitly state when to prefer this tool over alternatives or when not to use it. No alternative tools are referenced, so the agent must infer the use case from 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, so the description doesn't need to cover safety. It adds value by specifying the exact data fields returned (zone type, ratios, height limits), but does not disclose potential error behavior or output format. This is similar to the get_calls example where scope is added but not full return 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 concise and front-loaded with the core action and outputs. The Japanese translation repeats the same information, which is redundant but not overly wasteful. It earns a 4 rather than 5 due to the duplication.

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 simplicity, good annotations, and full schema coverage, the description adequately completes the picture. It lists the return values, but could optionally clarify the relationship between area and district (e.g., whether district is optional). This is a minor gap, so a 4 is appropriate.

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 clear descriptions for area, district, and prefecture. The description does not add additional meaning beyond the schema, so it stays at 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's function: 'Look up zoning (用途地域) for an area' and lists specific outputs (zone type, coverage ratio, floor area ratio, height limits). This specific verb+resource combination distinguishes it from siblings like get_chochou_profile or get_population_outlook.

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 for when to use this tool (when zoning information is needed) but does not explicitly mention alternatives or exclusions. It is clear enough for an agent to infer appropriate usage without confusion.

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 and non-destructive behavior, so the description only adds context about the UI type and view modes. It does not disclose additional behavioral traits such as whether it opens an external application, how it handles invalid parameters, or any side effects. This is minimal but acceptable given the annotation coverage.

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

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

The description is short and front-loaded with the core purpose. It is concise overall, but the Japanese version repeats the same information, which is slightly redundant. Still, it earns a high score for being compact and easy to parse.

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 output schema exists and annotations cover safety, the description is complete enough for an 'open' tool. It communicates the essential function and view options. However, it could mention how the parameters (like mode/layer) relate to the dashboard view, but the schema fills that gap.

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?

Input schema coverage is high (86%) with detailed descriptions for most parameters. The description itself does not add parameter-level meaning, but the schema provides adequate semantics. The baseline of 3 is appropriate because the description adds no extra parameter context beyond what the schema already supplies.

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?

Description clearly states the tool opens a visualization dashboard, specifying formats (2D map or PLATEAU 3D view) and UI (MCP Apps). The verb 'open' with the resource 'visualization dashboard' is specific and distinguishes it from sibling analytics tools, which focus on analysis rather than opening a dashboard.

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 specific scenarios, prerequisites, or exclusions. With many sibling tools that produce visual summaries or analyses, the description gives no hint about when opening a dashboard is preferable to using those.

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 scope limit of 5 areas and the output metrics, but does not disclose algorithm behavior, authentication needs, or rate limits. With annotations, 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 concise: one English sentence and one Japanese translation. The English sentence is front-loaded and informative. The Japanese duplicate adds slight redundancy but not significant bloat, so the overall structure remains 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?

There is no output schema, so the description must explain return values; it mentions expected return, risk score, and Sharpe ratio but not the output format. The tool has 5 parameters with enums, yet the description does not explain how optimizeFor or riskTolerance affect the optimization. It is adequate for a moderate-complexity tool but leaves 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 high (80%), with targets, optimizeFor, riskTolerance, and investmentHorizon all having descriptions. The tool description only adds the 'up to 5 areas' constraint, which already exists in the schema's maxItems. It does not explain parameter interactions or enums, but baseline 3 is appropriate given the 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 tool's purpose with a specific verb ('Optimize') and resource ('real estate investment portfolio'), and includes a scope ('across up to 5 areas'). It also mentions the return metrics (expected return, risk score, Sharpe ratio), which helps distinguish it from sibling tools like compare_prefectures or cross_analyze_real_estate_market.

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 multi-area portfolio optimization via 'across up to 5 areas,' but does not explicitly state when to use this tool vs alternatives or mention any when-not-to-use conditions. It provides no sibling tool references or exclusions, leaving usage guidance implicit.

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 10-prefecture scope and the types of scores, but does not describe return format, error conditions, or other behavioral details beyond what annotations imply.

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), front-loaded with the core action, and contains no redundant 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?

The description gives the overall purpose and geographic scope but does not explain what the input parameters should be or what the output scores look like. With no output schema, more detail on return values would improve completeness. The bilingual text helps but leaves operational gaps.

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

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

Schema coverage is high (80%), so baseline is 3. The description mentions 'manufacturing, office, retail' which does not exactly align with the propertyType enum (office, logistics, commercial, mixed), potentially causing confusion. No additional parameter insight is provided beyond the schema.

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

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

The description clearly states the tool predicts corporate demand scores for manufacturing, office, and retail, scoped to 10 prefectures. This is a specific verb+resource+scope combination that distinguishes it from sibling tools like forecast_land_price_trend or compare_prefectures.

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 provides no explicit guidance on when to use it over alternatives. The purpose is implied (when you need corporate demand predictions), but no exclusions or sibling comparisons are mentioned.

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 readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds behavioral detail about producing a compact markdown fallback and a dashboard with map/charts, which is useful context beyond the annotations, though it discloses no side effects or requirements.

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 in English and Japanese, front-loading the core function and usage directive. It contains no filler, and the 'Always use' instruction is direct and actionable.

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 presence of an output schema and annotations covering safety, the description provides sufficient contextual completeness. It specifies the tool's output components and the primary usage scenario, making it adequate for tool selection and 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?

All 5 parameters are covered in the schema with descriptions, so the baseline is 3. The description doesn't add explicit parameter semantics beyond the schema, though it mentions 'compact markdown fallback' which hints at the 'compact' parameter's effect, but not directly.

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 explicitly states the tool renders a ChatGPT-optimized real estate visual summary with map, charts, recommended next actions, and compact markdown fallback, using a specific verb ('Render') and resource ('real estate visual summary'). It also distinguishes itself by naming the exact user intents ('show, visualize, compare, continue in ChatGPT'), clearly separating it from siblings.

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

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

The description provides an explicit 'Always use this when...' directive, covering common user requests for visualization and comparison. However, it doesn't mention exclusions or alternative tools, despite siblings like compare_prefectures and detect_arbitrage_signals existing, so it stops short of full when-not guidance.

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?

The annotations already declare readOnlyHint=true and destructiveHint=false. The description adds context beyond this: it specifies the geographic scope (all 16 wards) and the behavior of cross-scanning major neighborhoods, plus the output ordering by yield. This gives the agent insight into the tool's operational scope, but it doesn't detail return format 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?

The description is a single bilingual sentence, front-loaded with the core purpose ('Renovation yield ranking'). It contains no redundant words and the format works well.

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 simple ranking nature, the description adequately communicates the tool's function and output (a ranked list of neighborhoods by yield). The annotations cover safety, and the schema covers parameters. However, there is no output schema, and the description could hint more at how inputs (like floor area, building age, property type) influence the ranking, but it's not required for basic use.

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 provides descriptions for 3 of 4 parameters (limit, floorArea, buildingAge), covering 75%. The description itself adds no parameter-specific meaning. The missing description for propertyType is mitigated by an enum, but overall the description does not enhance parameter understanding beyond the schema.

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

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

The description clearly states the tool's function: 'Renovation yield ranking: scan all 16 Nagoya wards to rank neighborhoods by yield.' This specifies the verb (scan/rank), resource (Nagoya wards/neighborhoods), and differentiates from similar sibling tools like analyze_renovation_yield, which likely focuses on a single property or area. The additional Japanese text reinforces the 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 description implies a clear use case (ranking renovation yield across Nagoya wards) but does not explicitly state when to use this tool over alternatives like analyze_renovation_yield or discover_opportunities. No exclusions or alternative recommendations are provided, so the guidance is only implicit.

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 adds meaningful behavioral detail by outlining the evaluation axes and the structured output (decision, red flags, negotiation points). No contradiction with annotations; the description goes beyond what annotations already provide.

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

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

The description is presented in both English and Japanese, but the Japanese portion is essentially a duplicate translation of the English. This redundancy means the second sentence does not earn its place. Still, the description is not overly long and is well-structured overall.

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 25 parameters, a nested object, and an output schema, the description adequately captures the overall evaluation scope and output categories. It correctly does not need to enumerate every input since the schema covers them, and the output schema handles return-value details. A small gap is the lack of guidance on when certain optional inputs are needed, but this is not critical.

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

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

The input schema has 100% description coverage for all 25 parameters, setting a baseline of 3. The description mentions some high-level concepts (e.g., asking price, land values) but does not add significant parameter-specific meaning beyond what the schema already documents.

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 specifies the tool's function as a comprehensive real estate purchase review, listing evaluation dimensions (asking price vs land values, yield, risk, future potential, contract terms) and output (5-axis scores, decision, red flags). However, it does not explicitly distinguish itself from sibling tools that focus on individual aspects (e.g., assess_property_risk, assess_contract_risk).

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: this is a purchase review tool intended for executives, covering multiple factors and returning a decision. It does not mention alternatives or exclusions, so it falls just short of a 5, but the context is explicit enough for a 4.

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 about the scope (10 prefectures) and scenario types, which is useful but not behavioral in the sense of disclosing rate limits, data sources, or return structure. It adds some context beyond annotations, so 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, delivering the core purpose in the first sentence, with a Japanese translation appended. It is not overly verbose, but the duplication of information in two languages adds slight redundancy. Overall, it is well-structured and front-loaded, earning a 4 rather than 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?

There is no output schema, so the description should provide details on what the tool returns. It mentions 'land prices and investment scores' as impact areas, but does not specify the output format, result structure, or how to interpret the simulation. With 6 parameters and no return value guidance, the description is incomplete for a tool of this complexity.

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 67%, with descriptions for city, scale, scenario, and prefecture. The description adds minimal semantics by enumerating scenario types (new stations, commercial facilities, population changes) and mentioning 10 prefectures, but these mostly overlap with the schema's existing enum and descriptions. It does not clarify horizon or includeMarkdown, so the baseline of 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's function: simulating the impact of new stations, commercial facilities, and population changes on land prices and investment scores. The verb 'simulate' and the resource 'impact on land prices and investment scores' are specific, and the mention of '10 prefectures' provides scope. However, it does not explicitly distinguish itself from sibling tools like simulate_aichi_future or forecast_land_price_trend, so it earns 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?

The description implies usage for what-if scenario analysis, but it does not explicitly state when to use this tool versus alternatives, nor does it mention exclusions or prerequisites. There is no guidance on when not to use it, so it falls to an implied-use case, matching a score of 3.

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 that it returns a candidate list of areas/tools/data sources, but gives no detail on result volume, pagination, or ordering. With annotations present, this provides only modest incremental transparency.

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 and front-loaded with the core action. The Japanese portion repeats the English meaning, but it also adds 'returns a candidate list', so it is not pure redundancy. Overall it is compact and readable.

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 catalog search tool with one parameter and safe annotations, the description adequately conveys scope and return type ('candidate list'). It does not mention result formatting or limits, but the absence of an output schema is partially compensated by the description's statement about returning candidates.

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 already documents the single 'query' parameter with examples and notes that natural language is acceptable. The description adds no new parameter information beyond the schema, so a baseline of 3 is appropriate.

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

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

The description states a specific verb ('search') and resource ('real estate data catalog') plus the kinds of things found ('areas, tools, and data sources'). This clearly distinguishes it from sibling 'search_area_candidates', which is narrower in 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?

It is clear that this tool is for searching the catalog, but there is no explicit guidance on when to prefer it over alternatives like 'search_area_candidates'. Usage context is implied by the description but not stated as a decision rule.

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; the description adds that matching is partial-text and supports hiragana. It does not contradict annotations, but it omits return shape or edge-case behavior, so transparency beyond annotations is modest.

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 English description is two short, front-loaded sentences with no filler, though the Japanese translation duplicates the same content. It remains compact and scannable.

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?

This is a simple search tool with annotated read-only safety and fully documented parameters, but with no output schema the description only says it returns 'valid candidates' without specifying the return format or whether results are ordered; 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?

All three parameters are documented in the schema (query, prefecture, limit) with examples and bounds. The description adds no parameter-specific meaning beyond restating partial-text and hiragana support, so it meets the baseline 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 uses a specific verb ('Search') and identifies the resource ('municipality name candidates') with the matching mode ('by partial text') and hiragana support, making its scope clear relative to broad siblings like '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?

The description implies an autocomplete/lookup use case but provides no explicit guidance on when to use it versus sibling tools such as 'search' or 'get_zoning_info', nor any exclusions.

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 no safety concerns. The description adds the output format (Markdown report) and the scope of scenario inputs, which is useful behavioral context beyond annotations. 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 concise and front-loaded with key information. However, the Japanese translation duplicates the English text, adding minor redundancy. Still, it is efficient 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 tool with no output schema, the description adequately communicates that it returns a Markdown report and which factors are simulated. Annotations and schema cover safety and parameters. While the report's structure is not detailed, it is sufficient for this simulation 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?

Schema description coverage is 75%, covering city, horizon, and scenarios with meaningful descriptions and enums. The tool description adds little beyond what the schema provides; the scenario names are already listed in the enum. Thus, the schema does the heavy lifting.

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 and resource: 'simulate' the future value of Aichi based on four named projects' impact on land prices, outputting a Markdown report. This distinguishes it from sibling tools that analyze other regions or aspects.

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

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

The description establishes a clear context: use this tool when modeling the combined effects of the listed Aichi infrastructure projects on land prices. It does not explicitly mention alternatives or exclusion criteria, but the specificity provides adequate usage guidance.

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 the tool read-only. The description adds that it uses external PLATEAU 3D building data and SunCalc, implying network/data dependencies, and notes it analyzes surrounding building impact. However, it does not disclose output format, performance, data coverage limitations, or other behaviors, so it provides only modest added value beyond annotations.

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

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

The description is exceptionally concise with two short sentences that complement each other: the English states the core function and data sources, while the Japanese adds the analysis goal. It is front-loaded and contains no fluff, earning 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?

With 7 parameters and no output schema, the tool should at least hint at what the simulation returns (e.g., a score, image, or report). The description omits any mention of return values or how results are presented, which is a significant gap for an agent deciding how to use the tool within a large real-estate toolset.

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 6 of 7 parameters described. The description itself does not elaborate on any parameters, but the schema handles most semantics. It does add context that the simulation depends on building data and sun position, aligning with lat/lng/dateTime. 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 tool performs sunlight/shadow simulation using PLATEAU 3D buildings and SunCalc, with the Japanese text adding that it analyzes the impact of surrounding buildings. This specific verb+resource+scope distinguishes it from all sibling tools, none of which focus on simulation or sunlight 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?

Usage context is implied by the name and description: the tool is for simulating solar impact from building shadows. However, it does not explicitly state when to use this tool over alternatives, nor does it mention any exclusions or comparisons to sibling tools like scenario_what_if or simulate_aichi_future.

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 provide readOnlyHint=true and destructiveHint=false, lowering the burden. The description adds valuable behavioral context: what inputs are accepted (loan interest rate, LTV, rent, etc.) and what outputs are returned (NOI, debt service, after-tax cash flow, DSCR, IRR, equity multiple, sensitivity). It does not contradict the annotations and gives a clear picture of the calculation scope.

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 in English followed by a brief Japanese translation. Every element earns its place: inputs, model horizon, and outputs are all covered without redundancy. It is front-loaded with the main verb and resource, and the bilingual format is efficient for the likely user base.

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 high complexity (17 parameters, nested objects) and the presence of an output schema, the description adequately covers the tool's purpose, inputs, and outputs. It does not dive into tax specifics or sensitivity methodology, but the output schema and parameter descriptions fill those gaps. An explicit note about the 'exit cap rate optional' behavior would be nice, but the schema covers it.

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 baseline is 3. The description lists broad input categories (interest rate, LTV, rent, vacancy, expenses, tax, depreciation, exit assumptions) but does not add detailed parameter-level semantics beyond what the schema already describes. It does not compensate for any gaps because there are none, but it also adds no extra clarity.

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 ('simulate' / '試算') and a precise resource ('Leveraged 10-year real estate pro-forma' / '10年の年次収支'). It distinguishes itself from siblings by specifying debt-related outputs (DSCR, IRR, equity multiple) and leveraged inputs (LTV, loan), which are not present in sibling names. This is a clear, specific 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 context by explicitly listing the financial model (leveraged 10-year pro-forma) and key outputs, allowing an agent to infer when to use it (e.g., when debt financing and cash-flow metrics are needed). However, it does not explicitly mention alternatives or exclusions relative to sibling tools like scenario_what_if or portfolio_optimizer, so it stops short of a 5.

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