不動産競売 構造化データハブ — Japan real-estate auctions

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

Annotations already indicate readOnlyHint=true and destructiveHint=false. The description adds that it is 'information-only' and 'not a paid intermediary,' providing context about the tool's nature and constraints, thus going beyond the annotations.

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

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

The description is very concise: it starts with the core purpose, then lists stages and constraints in a structured way. Every sentence adds value, and there is no redundancy or fluff.

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

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

Despite lacking an output schema, the description covers all necessary aspects: purpose, stages, default behavior, and a critical caveat (not combining with another tool). Given the tool's complexity (3 parameters, single enum), it provides complete guidance for an agent to use it correctly.

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

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

Schema coverage is 100%, so baseline is 3. The description adds significant meaning by explaining each stage (e.g., 'post_acquisition (default — 落札後の所有権移転登記; 司法書士が法律上ほぼ必須)'), which goes beyond the schema's enum labels.

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

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

The description clearly states the tool returns practitioners for auction-related stages, with specific resource ('士業') and verb ('返す'). It distinguishes from siblings by focusing on practitioner lookup, whereas siblings handle auction details, court directory, sales listings, and auction searches.

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 lists four specific stages with defaults, providing clear when-to-use context. It also explicitly warns against combining results with a grants-side tool, offering an important exclusion. However, it does not explicitly state when to prefer alternative tools (e.g., get_court_directory).

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, idempotentHint=true. Description adds behavioral details like derived fields (bid_floor_jpy = base × 80%) and mentions _canonical for citation, providing 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?

Description is concise: one sentence in Japanese and English, followed by a structured list of returned fields. 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?

Without an output schema, the description lists key return fields, providing sufficient context for an agent to understand what the tool returns. Coverage is adequate for the tool's 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?

Schema coverage is 100% for the single parameter case_id. Description enhances it with a concrete example and minimal length constraint, clarifying expected format.

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 explicitly states 'Fetch one auction by case_id' and lists specific return fields, clearly distinguishing from sibling tools (search, list, find).

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?

Description provides usage context by naming the required parameter and giving an example. While it doesn't explicitly state when not to use, the focus on single-case retrieval and the sibling names imply appropriate usage.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, establishing the safety profile. The description adds context (Japanese district court, lookup by code) but does not disclose additional behaviors such as rate limits or authentication requirements. With annotations present, this is adequate.

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 very short (two sentences, bilingual) and front-loaded. It conveys the essential information efficiently, though the Japanese and English versions are somewhat redundant.

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 tool with one parameter, full schema coverage, and informative annotations, the description fully covers what is needed. It tells the agent what the tool does and how to use the parameter, leaving no 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 100%: the parameter 'court_code' is documented with examples. The description only restates 'by code' without adding new meaning. Baseline 3 is appropriate since the schema already 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 the tool's purpose: to retrieve Japanese district court directory info (contact/jurisdiction) by code. It uses specific verbs (look up, 取得) and distinguishes itself from sibling tools that focus on auctions.

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 court code is available and directory info is needed, but it does not provide explicit when-not-to-use guidance or alternatives. Since siblings are all unrelated (auctions), the lack of exclusions is acceptable but not ideal.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint, so the safety profile is clear. The description adds the sorting behavior (ascending) and default/max values, which is minor 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 concise (two English sentences plus a Japanese phrase). It front-loads the purpose and includes parameters and use case. The Japanese phrase may be redundant for English contexts but does not harm conciseness.

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

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

With no output schema, the description should hint at return structure. It says 'list auctions' but does not specify fields. It covers the input and purpose adequately but lacks details on what is returned.

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 descriptions for both parameters (limit, days_ahead) including defaults and bounds. The description only echoes the days_ahead default and max, adding no new parameter meaning. 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 verb 'list' and the resource 'auctions', and specifies the time window (next N days, default 14, max 90) and sorting. This distinguishes it from siblings like search_auctions (likely more filtering) and get_auction_detail (single item).

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 mentions 'Useful for investment screening / calendar exports', providing context for when to use. It does not explicitly state when not to use, but the sibling tools imply alternatives. Clear context but lacks 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 indicate readOnlyHint, idempotentHint, and destructiveHint. The description adds that data comes from BIT (bit.courts.go.jp) but does not disclose additional behaviors like pagination, rate limits, or default sorting beyond what is in the schema.

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

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

The description is a single sentence front-loaded with the main purpose and lists filters and return fields efficiently. However, the mix of Japanese and English and the comma-separated style could be clearer.

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 no output schema, the description explains return fields (case_id, court, address, etc.) and mentions data source. It lacks guidance on pagination and sorting default, but overall is sufficient for a search tool with good annotations.

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 45%, and the description lists most filter categories (keyword, prefecture, court_code, property_type, price range, bid_period_only) but omits sort, limit, offset, and status. It adds context by grouping filters but does not fully compensate for the coverage gap.

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

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

The description clearly states the tool searches Japanese real estate auction properties (競売物件検索) with specific filters and return fields, distinguishing it from sibling tools that focus on details or directories.

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?

While the description lists filters and return fields, it does not explicitly guide when to use this tool versus siblings (e.g., get_auction_detail for single auction details). The usage context is implied but not explicitly stated.

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