AI Furniture Hub

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

With no annotations, the description carries the transparency burden. It discloses output content (coordinates, rotation), limitations (door/flow ignored), and additional warnings (carry_in_warnings with risk levels). This gives the agent a good sense of behavior beyond just the tool's existence.

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 three sentences, front-loaded with the usage scenario, followed by process, output, limitations, and warnings. Every sentence adds distinct information with no redundancy.

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

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

Given there is no output schema, the description covers the main inputs, output type (coordinates/rotation), caveats (traffic not considered), and special warnings. It lacks details on optional parameters and exact output structure, but is sufficiently complete for an agent to invoke the tool correctly for typical 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?

Schema coverage is only 43%, so the description must compensate. It clarifies that room dimensions are effective dimensions, and that items list requires width/depth/count. However, it does not explain grid_step_mm, margin_between_mm, or wall_clearance_mm, leaving gaps for those optional 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 explicitly states that this tool is for checking if furniture fits, using room dimensions and a furniture list, and specifies that it returns coordinates and rotation. This clearly distinguishes it from siblings like suggest_by_space by focusing on placement simulation rather than product suggestion.

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 concrete usage example ('部屋にベッドとデスクは入る？'), explains that doors and traffic flow are not considered (so results are estimates), and instructs how to handle carry_in_warnings. It does not explicitly name alternative tools, but the conditions for use are clear.

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?

There are no annotations, so the description carries full behavioral disclosure. It explains conditional behavior (catalog matches add inner dimensions, compatible storage, buy_guide), how buy_guide's decision_hint is reflected in the comparison recommendation, and instructs presenting affiliate_url to the user. This goes beyond a simple statement and gives actionable behavioral context.

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

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

The description is compact and front-loaded, starting with the primary usage condition and example. Each sentence provides distinct information (output, conditional add-ons, recommendation logic, user instruction) without fluff or redundancy. The structure is logical and easy to parse for an AI agent.

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

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

Given no output schema and no annotations, the description needs to explain return values and behaviors. It does so: describing the parallel comparison table, default and conditional fields, and the affiliate_url presentation directive. It covers the tool's main behavior and expectations sufficiently for an agent to invoke and interpret results.

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 baseline is 3. The description does not add substantial meaning to the parameters beyond the schema; it mentions default comparison aspects (price, size, reviews, load capacity) but does not elaborate on the intent, keywords, or compare_aspects parameters themselves. It neither compensates nor hurts.

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: comparing 2-5 products, with a concrete example ('NクリックとKALLAXどっちがいい？'). It names the specific resources compared (price, size, reviews, load capacity), and the title reinforces '並列比較' (parallel comparison). This distinguishes it from siblings like get_product_detail (single product) and search_products (searching).

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 when-to-use guidance: '2〜5製品を比較するときに呼ぶ' (call when comparing 2-5 products), with an example query. However, it does not explicitly mention when not to use this tool or point to alternatives, so it lacks explicit 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?

With no annotations, the description carries the full burden. It discloses several behavioral traits: calculation of counts/prices, provision of coordination tips and persona_hints, carry_in check for large shelves, the need to advise users when risk=warning/critical, and the requirement to present affiliate_url. This is rich behavioral disclosure, though it could mention error handling or what happens when no matches are found.

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 three sentences long, front-loaded with trigger examples, and each clause adds value. It is dense but structured logically, covering triggers, main calculation, additional features, and required actions. Slightly more compact would be ideal, but it 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 convey what the tool returns. It lists total count/price, coordination tips, persona_hints, carry_in, risk levels, and affiliate_url, which gives a good picture of the output. It does not describe the exact format/structure of the response, but given the tool's complexity, the description is adequately complete.

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

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

Schema description coverage is 100%, so all parameters already have descriptions. The tool description adds context about using shelf internal dimensions and installation location, but it does not provide additional syntax or format details beyond the schema. It meets the baseline for schema-heavy parameter documentation.

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: it calculates the number of storage boxes that fit in a shelf from internal dimensions, computes total count/price, and provides coordination tips and persona recommendations. It also gives explicit trigger examples like 'What box fits this shelf?' which makes it unmistakably distinct from 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?

The description provides clear context for when to call the tool via example queries ('「この棚に合うボックスは？」「カラーボックスの整理方法」'), and further specifies conditional usage for large shelves with carry_in and risk warnings. However, it does not explicitly mention when not to use it or contrast with alternatives, so it misses the full 'when-not/alternatives' 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?

With no annotations provided, the description carries the full burden of explaining behavior. It does so by enumerating the checks performed and the output format. However, it does not disclose potential side effects (e.g., whether the tool fetches the URL, handles errors, or requires network access), which is a minor gap but not severe.

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 front-loaded with the main verb 'diagnose' and then efficiently lists checks and output. The final demo sentence adds context without excess. It is slightly longer than absolutely necessary but every sentence contributes value.

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?

Since there is no output schema, the description appropriately explains the return format (score and grade) and the key checks performed. The tool's complexity is moderate, and the description covers the essentials well, though it could note potential limitations (e.g., invalid URLs, network failures).

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 describes both parameters with 100% coverage ('url' and 'intent'), so the baseline is 3. The description does not add extra meaning to the parameters beyond the tool's overall purpose; for example, it does not clarify what should go in 'intent' beyond the schema's vague 'why diagnosis is needed'.

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: diagnosing how visible a website is to AI agents given a URL. It lists concrete checks (llms.txt, robots.txt, structured data, OGP, etc.) and the output (0-100 score, A-F grade). It is distinct from sibling tools, which focus on physical products, measurements, or 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 provides a clear use context: it can be used as an AIO agency demo to show clients how AI sees their products. However, it does not explicitly state when not to use the tool or mention alternative tools, so it stops short of a full 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?

No annotations are provided, so the description must carry the behavioral transparency burden. It does so by explaining the data source (demand_signals), the combination logic (bundling miss and tight_fit), and the output dimensions (scene, dimension band, category). The word '返す' (returns) implies a read-only operation. It does not mention sorting or limit behavior, but those are covered by 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 compact at two sentences: the first states what the tool does, the second states when to use it. Every clause contributes value, and there is no repetitive or filler 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?

The description gives a good high-level overview but lacks details on the return structure, sorting, or how 'miss' vs 'tight_fit' are defined. Since there is no output schema, the description alone is expected to explain what the agent will receive; it only partially does so. It is adequate but leaves gaps for a complex analytical 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 100%, so the baseline is 3. The description adds some context by linking outputs to scene/dimension/category and explicitly mentioning tight_fit, but it does not meaningfully deepen the understanding of the 'intent' or 'limit' parameters beyond their schema descriptions.

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: it bundles 'miss' and 'tight_fit' signals from demand_signals and returns product gaps by scene, dimension, and category. This distinguishes it from sibling tools like summarize_demand_signals, which presumably summarizes signals rather than finding specific gaps.

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 concrete use cases: identifying Amazon listing candidates, in-house development candidates, and priority dimension data bands to collect. It does not explicitly state when not to use the tool or mention alternatives, but the context is clear enough for an agent to decide when this tool applies.

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?

Since no annotations are provided, the description carries the full burden. It discloses that the tool returns two types of results (catalog successors and Rakuten search results) and instructs presenting affiliate URLs. However, it does not mention any potential side effects, authentication needs, or failure scenarios, which would be useful for a read/search tool without annotation support.

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 front-loaded with a clear trigger phrase, followed by output details and a critical instruction about affiliate URLs. Every sentence adds value, though it is slightly longer than the minimal two-sentence ideal. No 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?

With no output schema and no annotations, the description should explain return values and handling. It mentions the two result sources and explicitly instructs presenting affiliate_url. However, it leaves out details like result format, limits, or error handling, which would make the tool easier to use 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?

The schema already provides descriptions for both required parameters (query and intent), covering model number/product name and the reason for replacement. The description adds no extra parameter-level context, so baseline 3 is appropriate.

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

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

The description clearly defines the tool's role: finding successor/alternative products for discontinued or unavailable model numbers. It explicitly specifies it returns catalog successors and Rakuten search results, which distinguishes it from generic product search siblings like search_products or get_related_items.

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 explicitly states when to call the tool: when a model number is not available or a shelf is discontinued. It also advises final confirmation via the manufacturer's official website. It does not mention when not to use it or alternative tools, but the trigger scenarios are clear.

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 no annotations, the description must disclose safety, permissions, and response traits. It does mention that the tool returns product_ids for each product and that further details can be fetched via other tools, but it does not explicitly state it is read-only or describe the full response structure (e.g., set metadata, pagination). It adds behavioral context (four types, follow-up usage) but has gaps.

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 three sentences covering examples, type definitions, and integration with other tools. Every sentence provides useful information without fluff, and the structure is front-loaded with relatable examples.

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 6 parameters and absence of annotations or an output schema, the description should explain return structure thoroughly. It states that product_ids are included and that other tools can be used for details, but it does not describe the overall response shape (e.g., list of sets, fields like set name/description) or any pagination/sorting. The examples and type definitions make it minimally viable but with these 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?

The schema covers 100% of parameters, so the baseline is 3. The description adds value by explaining the 'type' enum with examples (IKEA-style for room_preset, substitute for hack_set) and by showing how intent, scene, and budget combine in a query like 'budget 50k to build a study'. This enriches parameter semantics beyond the schema's one-line descriptions.

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 it returns curated set proposals and names four types (bundle, room preset, influencer pick, hack set). It provides concrete example queries and distinguishes from sibling tools by noting that product_ids can be used with get_product_detail or search_rakuten_products for details.

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

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

The description gives clear context on when to use: when the user asks for a set of items like 'everything needed for a new life' or 'YouTuber desk tour products'. It also explains the four subtypes, helping the agent select the right type. It does not explicitly say when not to use alternative search tools, but the examples imply it is for curated bundles rather than individual product search.

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?

No annotations exist, so the description must carry behavioral disclosure. It states the tool returns recommended products, adds Rakuten review trends, and instructs that affiliate_url must be presented to the user. This is useful but doesn't mention read-only behavior, limits, or error handling. It adds some behavioral context but not comprehensive.

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

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

Two sentences, front-loaded with usage triggers, and no redundant information. Every phrase earns its place.

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

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

No output schema exists, so description is responsible for return expectations. It covers the key output elements (product recs, category/brand filtering, Rakuten trends, affiliate URL). However, it doesn't specify response structure or edge cases, and there are no annotations, so it's not fully complete. A 4 reflects sufficient information without being 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 coverage is 100%, so baseline is 3. Description adds context by showing sample intents ('Which shelf?') and clarifying that category/brand filter results and include_rakuten_trending relates to the Rakuten trends. It adds small value beyond the schema, but not enough to raise above 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 returns recommended/popular products filtered by category/brand, with extra info like compatible storage/consumables and Rakuten review trends. It gives usage trigger examples ('おすすめの棚は？', '人気のキッチン家電は？'), making the purpose specific. However, it doesn't explicitly distinguish itself from sibling search tools like search_products, so it stops short of a 5.

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

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

Provides explicit trigger contexts ('おすすめの棚は？', '人気のキッチン家電は？') indicating when to invoke. It explains filtering by category/brand but does not mention alternatives or exclusions, so it gets a 4 rather than 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?

With no annotations, the description carries the transparency burden. It discloses useful behavioral traits: the response includes an affiliate_url for purchase links, and related products are automatically suggested. It does not mention read-only status or error behavior, but for a 'get' tool this is less critical and the provided details exceed the bare minimum.

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 well-structured with clear markers (【重要】,【収益化】) and front-loads the primary purpose. Each sentence adds distinct value, though the monetization instruction is perhaps extra; however, it is still concise and not 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 tool with only 2 parameters, no output schema, and no annotations, the description covers the essential purpose, highlights key return elements (affiliate_url, related products), and explains the intent requirement. It lacks explicit error handling or full response details, but is sufficient for a simple detail-fetch 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 coverage is 100%, so the baseline is 3. The description adds meaningful guidance for the intent parameter, specifying it should contain the reason (e.g., '購入前の最終確認') and giving examples. It also explains the purpose of id (商品ID), which aligns with the schema and enhances usability.

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+resource: '商品IDを指定して、特定の家具・収納商品のフルスペック（寸法・価格・在庫・素材など）を取得します'. It specifies exactly what the tool does (retrieve full specs by product ID) and distinguishes from siblings like search_products or get_related_items by focusing on a single product's detailed data.

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

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

The tool's usage is implied: it is for when you have a product ID and need full details. However, it does not explicitly state when to use it over sibling tools (e.g., search_products to find IDs first) or provide exclusions, leaving some ambiguity for the agent.

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 no annotations, the description carries the full burden. It discloses meaningful behavior: results are split into required and recommended groups, each item comes with Rakuten search results for immediate suggestion, depth=2 expands to 'related of related', and required=true items must be communicated to the user. This goes beyond a simple verb and gives actionable behavioral rules.

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 well-structured: it opens with the primary use case, then explains the output split, the Rakuten integration, the depth behavior, and the mandatory instruction about required items. Every sentence adds value, and the most important information is front-loaded.

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 has 5 parameters and no output schema, the description covers the main aspects: when to use, what it returns, and a key rule. However, it lacks details on how product_id and keyword interact (e.g., which takes precedence, whether both can be provided), and it doesn't describe the response structure beyond the required/recommended split. This is a minor gap but 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?

Schema coverage is 100%, so the baseline is 3. The description adds some context to parameters (e.g., depth=2 expansion, Rakuten search results related to include_rakuten), but essentially restates what the schema already documents. It doesn't clarify the precedence or mutual exclusivity of product_id and keyword, so it doesn't elevate above baseline.

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

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

The description clearly states the tool's purpose: to suggest complementary items (accessories, protective materials, parts) after finding a product with search_products. It distinguishes itself from siblings by focusing on the 'what else do you need?' use case and explicitly separates required vs recommended items.

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 usage context: call it after using search_products to find a product. It doesn't explicitly name alternatives, but the context ('他に何が必要？') and the reference to search_products make the intended workflow clear. It implies not to call it before product discovery.

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 no annotations provided, the description carries the full burden. It discloses that the tool expects pre-extracted feature text (not raw images), searches catalog + Rakuten, and returns candidates conditionally (with extra info when model number is identified). However, it does not mention any limitations, error handling, or side effects, and since it's a quest-like operation, the lack of explicit read-only confirmation is a minor gap.

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 highly concise, consisting of two sentences that pack in the trigger scenarios, input format, data sources, and output characteristics. It is front-loaded with usage examples and avoids unnecessary fluff, making it easy to scan and understand quickly.

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

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

The tool has no output schema, so the description must explain return values. It does mention that candidates are returned and that internal dimensions, consumables, and compatible box info are included when model number is identified. However, it lacks details on the structure of the response or how to interpret multiple candidates, which is a minor gap given the tool's 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%, so the baseline is 3. The description adds context that the 'features' parameter should contain brand/color/number of shelves/material/estimated size, aligning with the schema. It does not provide additional syntax or format details beyond what the schema already documents, but it reinforces the intended usage of the 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 tool's purpose: identifying a product from photo-derived feature text, with specific example queries ('この写真の棚は何？'). It specifies the resource (products from catalog + Rakuten) and distinguishes itself from generic search tools by focusing on image-based identification. The addition of model number, internal dimensions, and consumables info further clarifies its specialized role.

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 explicitly says when to call it ('「この写真の棚は何？」「持ってる棚に合うボックスを知りたい」のときに呼ぶ'), providing clear use cases. It does not explicitly mention alternatives or when not to use it, but the context is specific enough that an agent can infer differentiation from sibling search tools.

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

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

No annotations are provided, so the description carries the full burden. It discloses the output type (all 31 categories, product counts, brands) and the filtering capability, but does not explicitly state that it is a read-only operation, nor does it mention any limitations, error behavior, or rate limits. For a list tool, 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 three short sentences, front-loaded with the main purpose and usage trigger. Every sentence earns its place: it states the trigger, the return value, and the workflow. No redundant or vague 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 tool is simple (2 parameters, no output schema), and the description covers the key context: what it returns, how to use it, and how it fits into the larger workflow. It does not explain the exact structure of the returned data, but since no output schema exists, the description does its job adequately.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds meaning by explaining that the category_filter parameter allows retrieving a product list for a specific category. It does not elaborate on the 'intent' parameter, but the schema already describes it as 'the purpose of viewing categories'. The added value slightly exceeds baseline.

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

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

The description clearly states the tool's purpose: to list all 31 categories with product counts and brands, and to serve as an entry point for category exploration. It distinguishes itself from search_products by positioning itself as the first step before using that tool. The verb '返す' (return) and specific resources (categories, counts, brands) make it unambiguous.

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

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

The description explicitly states when to use it: when the user asks what can be searched or what categories exist. It also provides a clear usage flow: first understand categories, present to user, then proceed to search_products. However, it does not explicitly mention when not to use it or alternative tools beyond search_products, which would make it 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the method (pixel ratio), the AI's role (Vision analysis and passing pixel values), supported reference object dimensions, and confidence handling. It does not fully detail edge cases or the exact return structure, but it covers the key behavioral traits.

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

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

The description is dense but well-structured: usage trigger, calculation method, AI role, supported reference list, downstream workflow, and confidence fallback. Each sentence provides useful information, though it is slightly long. It is appropriately sized for the tool's complexity.

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 complex tool with 7 parameters, nested objects, and no output schema. The description covers the full workflow: what to pass (pixel dimensions), what the tool computes, how to use the result, and what to do in low-confidence cases. It gives sufficient context for an agent to invoke it correctly and use its 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 description coverage is 100%, so the baseline is 3. The description adds extra meaning by listing actual dimensions for each supported reference object (e.g., 名刺 91×55mm), clarifying that pixel values are to be read by Vision, and explaining manual_dimensions_mm as an override. This goes beyond the schema's basic descriptions.

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: 'ピクセル比率から対象物の実寸(mm)を逆算する' – it estimates actual dimensions from a photo with a reference object. It uses specific verbs and distinguishes itself from sibling tools (which handle search, comparison, or storage) by being the only measurement tool.

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

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

It explicitly states when to call: '「写真を撮ったので寸法を測りたい」「この隙間に合う棚を探したい」のときに呼ぶ'. It also provides integration guidance: passing search_dimensions to suggest_by_space or coordinate_storage, and advises telling the user to measure manually if confidence is low.

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 no annotations provided, the description carries the full burden. It discloses that the tool returns a URL only, not product data, and that SearchIndex is auto-selected. It also instructs presenting the URL. However, it does not mention potential error cases or behavior for invalid parameters, which would add more transparency. Overall, good but not exhaustive.

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 three concise sentences: when to use, what it does (URL generation, no data), and an instruction. No filler, front-loaded purpose. Every sentence contributes meaning.

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 covers the essential purpose, usage context, and expected output (affiliate_url), which is sufficient for selecting and invoking the tool. However, it does not mention that the tool is specifically for furniture/storage products (though the title does), and it lacks edge-case guidance for empty search results. Minor gaps but overall 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?

The schema covers 100% of parameters with descriptions, so the baseline is 3. The description adds context about SearchIndex auto-selection from category, but does not explain sort or price parameters beyond the schema. It does not need to repeat schema details, so it meets the baseline.

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

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

The description clearly states the tool generates an affiliate URL for Amazon search results and explicitly notes it does not return product data. This distinguishes it from sibling tools like search_products or search_rakuten_products. The verb 'generate' and resource 'Amazon search results page URL' are specific.

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 explicitly says when to use this tool: 'when the user wants to buy on Amazon or when not found on Rakuten'. It also provides an alternative (Rakuten) and instructs to present the affiliate_url to the user. This is clear guidance for selection and invocation.

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?

No annotations are present, so the description carries the full burden. It usefully discloses result-handling behaviors: using related_items_hint, conveying buy_guide's best_for/avoid_if, reporting seasonal_hints/active_sales, and presenting affiliate_url. It does not mention pagination, sorting, or whether the operation is read-only, but '横断検索' implies query-only.

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 well-structured paragraph. Every sentence carries a distinct behavioral or usage instruction (triggers, filters, related items, buy guide, sales, color aliases, affiliate URL). It is longer than minimal but not bloated, and the trigger examples are front-loaded for quick scanning.

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 compensates by hinting at result fields (related_items_hint, buy_guide, seasonal_hints, active_sales, affiliate_url) and dictating agent actions for each. It lacks explicit no-results handling or pagination info, but covers the key downstream behaviors well.

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 detailed descriptions for all 14 parameters. The description adds some context by listing filter dimensions (keyword, size, price, color, brand) and trigger phrases that map to intent and size params, but this is largely redundant with the schema. Baseline 3 is appropriate.

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

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

The description opens with concrete user utterances ('棚が欲しい', 'Dysonのドライヤー', '幅40cmに入るもの') and explicitly states it cross-searches a catalog of 31 categories and 80+ brands by keyword, size, price, color, and brand. This clearly distinguishes it from sibling tools like search_amazon_products or get_related_items.

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?

Provides explicit trigger phrases and scope (internal catalog, 31 categories, 80+ brands). It also instructs when to use get_related_items for accessory chains based on related_items_hint. However, it does not explicitly contrast with external marketplace searches or other siblings like identify_product.

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 no annotations provided, the description carries the full burden. It discloses that the tool uses an external API, returns real-time data with price/reviews/images, and mandates presenting the affiliate_url to users. However, it does not mention potential side effects, error handling, or limitations like rate limits or coverage gaps, leaving some behavioral aspects undisclosed.

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 three concise Japanese sentences, front-loaded with the usage trigger, then the function, and finally a critical output instruction. No redundant or filler content; every sentence earns its place.

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

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

Given the tool has 6 parameters and no output schema, the description covers the core context: when to call, what it does (real-time search returning price/reviews/images), and a specific behavioral requirement (present affiliate_url). It lacks details on result count, pagination, or how to handle empty results, but the schema and available context cover some of this. Overall, it is reasonably complete 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?

The input schema provides complete descriptions for all 6 parameters (100% coverage), so the description does not need to compensate. The description adds no extra meaning about parameters; it only mentions output characteristics like price and reviews, which are not directly tied to parameter usage. Thus, baseline 3 is appropriate.

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

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

The description clearly states a specific action: call when you need products not in the catalog or latest price/stock, and perform a real-time search via Rakuten API returning price, reviews, and images. It distinguishes from sibling tools like search_amazon_products and search_products by emphasizing the Rakuten source and real-time nature.

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 trigger condition: 'カタログにない商品や最新価格・在庫が必要なとき' (when you need products not in catalog or latest price/stock). This clearly implies when to use, but it does not explicitly name alternative tools or state when not to use it, so it falls short of a full 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?

With no annotations provided, the description carries the full burden and does so excellently. It discloses rotation fit, automatic coordination plan generation, carry_in route checks for large items, risk level handling (warning/critical), and the requirement to present affiliate_url. These are behavioral traits beyond a simple search action and help the agent understand what to expect and what actions to take.

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 but information-dense, covering the trigger, core behavior, special features, and necessary user-facing actions in just a few sentences. Every sentence adds value, with no padding or repetition. It is front-loaded with the primary use case, making it easy to scan.

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 there is no output schema and no annotations, the description compensates by describing return values (products, coordination plans, carry_in info, affiliate_url) and instructs the agent on how to handle risk levels and present affiliate links. It covers all critical aspects of the tool's behavior for an agent to invoke and 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?

The input schema already provides descriptions for all parameters, giving 100% coverage, so the baseline is 3. The description adds little parameter-specific meaning beyond confirming dimensions are in mm and that rotation of width/depth is considered—which is more of a behavioral trait. It does not clarify any parameter ambiguities 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 purpose with a specific verb and resource: it suggests products that fit in a space based on dimensions. It distinguishes itself from siblings by explicitly saying this is for 'space-based' searches (スペース起点で探すとき) and describes cross-category return behavior. The concrete example ('洗面所の幅45cm×奥行30cmの隙間') makes the use case unmistakable.

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 provides a clear when-to-use trigger: call when searching with space as the starting point, with a concrete example. However, it does not explicitly name alternative tools or state when not to use this tool, so it stops short of full guidance. The context is clear enough for an agent to distinguish from general product searches.

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?

No annotations are provided, so the description must convey behavioral traits. It describes the aggregation behavior and data sources, but does not disclose side effects, permissions, or output format. Since it is a read-only summarization, the lack of explicit safety guarantees is a minor gap, but the description gives a clear functional behavior.

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 and front-loaded with the primary function, followed by usage context. No redundancy or filler; every clause contributes meaning.

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

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

The tool has no output schema and no annotations, so the description is the sole source of context. It covers the tool's purpose, sources, and use cases, but omits expected output format or any limitations (e.g., data freshness, aggregation rules). This is adequate for simple use but leaves the agent guessing about the return value.

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 have schema descriptions (100% coverage), so the baseline is 3. The description adds only minimal context beyond the schema—it mentions 'scene' which aligns with scene_name, but does not elaborate on intent or limit semantics.

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

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

The description clearly specifies the tool's function: 'demand_signals を要約する' (summarize demand signals) accumulated from two source tools, and explicitly lists the aggregation dimensions (scene, fit state, safety flags). This differentiates it from sibling tools like get_popular_products or find_product_gaps.

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 states when to use: 'どのシーン・どの fit 状態・どの安全フラグが多いかを把握したいときに呼ぶ' and lists concrete use cases (analysis, weekly reports, product planning prioritization). It does not explicitly mention alternatives or when not to use, so it lacks the exclusionary guidance for a 5.

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