bimhouse

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 does disclose meaningful side effects beyond the schema: the build is also recorded in the scout-land, referral, and design-royalty ledgers, and that it delegates to create_house. It omits permissions/auth, irreversibility, and failure modes on already-occupied land.

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?

Three compact clauses with the action front-loaded, then mechanism, then side effects. No filler, though the '/earth' reference is only useful to agents that know that surface.

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 mutation tool with no annotations and no output schema, the description covers what it does and its ledger side effects, but leaves out error conditions, whether re-building on the same parcel is allowed, and what the caller receives back.

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 six parameters (including defaults for name, zoning, area_m2, and the template_id purpose) are already documented in the schema. The description only restates that zoning/area/name are optional and adds 'injects regulations', so a baseline 3 is appropriate.

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

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

States a specific verb and resource: build a house on a given parcel, with lat/lng required and zoning/area/name optional. It also explains the mechanism (injects coordinates and regulations into create_house), which lets an agent distinguish it from calling create_house directly.

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 mention of 'same API as /earth's build-on-this-land' implies the use case, and the input implies 'when you have coordinates'. But there is no explicit guidance on when to prefer this over sibling create_house, nor any exclusion or precondition (e.g. land must be unbuilt).

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 does substantial work beyond what structured fields offer: it discloses the Bearer API key requirement, where to obtain the key (/console), the free tier (first ¥300 / 5 calls) and top-up path (/credits), and the response language. What is missing is failure behavior (what happens when credits run out or auth fails) and response shape.

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?

It is dense but front-loaded: purpose first, then auth, then billing, then domain scope, then parameters. Every clause carries operational information and there is no filler, though the billing detail is packed into a long sentence rather than separated.

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 2-parameter tool with no annotations and no output schema, the description covers purpose, auth, billing and domain well enough to call it correctly. Return-value behavior is the only notable gap, and with no output schema declared that gap is minor.

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

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

Schema description coverage is 100%, so the schema already documents both message and history. The description restates the parameters and lightly clarifies the history format as [{role, content}], but adds no semantics beyond the schema, so baseline 3 applies.

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

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

The description states a specific verb+resource: an AI chat that answers Japanese-language questions about architecture, BIM, building regulations, SIPs and MU. This clearly distinguishes it from the sibling CRUD-style tools like create_house or get_house_bim. It stops short of naming a sibling explicitly, which keeps it below 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 domain scope (architecture/BIM/regulations) implies when to use this and the alternatives are implicitly exclusive, but there is no explicit 'use this when X instead of Y' or statement of when NOT to use the chat. Auth and billing prerequisites are stated, but those are operational constraints rather than usage routing.

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 and does well: it discloses side effects (auto-placed elements such as 煙突・炉台・はしご, climate-based envelope upgrades, floor-count inference), the conditional REINFOLIB_KEY zoning injection, the private=false default, and the full return payload (slug, edit_token, viewer/json/permit URLs, features, site). Gaps remain: no permission/auth notes and no error behavior, and the claim that name or address is required conflicts with the schema's empty required list.

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?

Purpose is front-loaded in the first clause and nearly every sentence carries non-obvious behavior (geocoding, auto-generation, keyword triggers, return values). The heavy nested parentheses make it dense and slightly hard to scan, but there is little true filler.

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

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

For a 13-parameter creation tool with no annotations and no output schema, the description covers the important ground: entry conditions, auto-generation vs explicit elements, side effects, and the exact return payload. Remaining omissions (permission model, failure modes, edit_token lifecycle) are secondary given the richness supplied.

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, and the description mainly reinforces schema semantics (address-only workflow, elements pass-through). It does add genuinely new meaning for rooms (keywords that trigger feature placement) and floors ("平屋"/"2階建て" inference), which lifts it slightly but not to the top of the scale.

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 first sentence states a specific verb and resource (新しい物件 (bim.json) を作成する), and the body makes clear this is a full house-BIM creation/generation tool rather than a listing/read tool. It never names the sibling it is not (e.g. build_on_land), so differentiation from similarly-named tools is left to inference.

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 concrete usage conditions: pass only an address and geocoding plus auto-naming kick in; pass elements to store verbatim, omit them to auto-generate from lot dimensions; mention keywords in name/rooms to trigger feature placement. What is missing is any exclusion or pointer to alternatives such as build_on_land, so the agent has context but no explicit routing rules.

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 does real work: it discloses the Bearer auth requirement, that changes are immediately reflected in /catalog and search_catalog, and the insert-only constraint. It omits what happens on a duplicate-SKU attempt (error type) and whether the call is idempotent, which keeps this below 5.

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?

Front-loaded with purpose, then auth, side effects, and the insert-only constraint in a compact sequence. The category enumeration (サッシ/窓/…) slightly duplicates the category parameter's own description, a minor redundancy.

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

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

For an 18-param mutation tool with 100% schema coverage and no output schema, the description supplies the missing behavioral layer: auth, indexing side effects, and insert-only semantics. Error/duplicate behavior is the only notable 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 schema already documents all 18 params with examples and semantics. The description adds no param-level detail (defaults, constraints, nesting for spec) beyond naming categories, so the baseline 3 applies.

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

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

States a specific verb+resource (新しい製品 SKU を登録する) plus the domain (建材カタログ/products) and category examples, so an agent knows exactly what it does. Together with the insert-only note, it is clearly distinguishable from update_product, retire_product, and get_product without opening any schema.

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

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

Gives the essential context to use it: auth required, insert-only (no overwrite of existing SKU), and side effects on /catalog and search_catalog. It does not explicitly name update_product as the alternative for existing SKUs, which leaves the 'what do I do for an existing SKU' inference to 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?

No annotations are provided, so the description must carry the full behavioral burden. It does disclose the returned payload structure and the meta-only mode, which is genuinely useful, but says nothing about read-only safety, failure modes for an unknown slug, or result size for element-heavy properties.

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 tight sentences: the primary fetch behavior is front-loaded and the optional slim-mode caveat follows. Nothing redundant or padded.

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 two-parameter read tool with full schema coverage and no output schema, the description covers the resource identity, the payload contents, and the slim mode. Only edge-case behavior (unknown slug, large element arrays) is left unaddressed.

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 both parameters are already documented, which sets the baseline at 3. The description adds a little by restating that include_elements=false yields meta only, but that largely duplicates the schema's '要素を含めるか (既定 true)'.

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 names a specific verb (取得) and resource (物件の完全な bim.json v1) and spells out the payload shape (project メタ + elements 配列), so an agent knows exactly what comes back. It does not explicitly name the sibling list_houses as the alternative for enumeration — that reference lives only in the schema.

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

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

Usage is implied rather than stated: 'slug を指定して' and the include_elements=false toggle hint at when to use the slim mode, but there is no explicit when/when-not guidance or comparison to siblings like list_houses or get_land_listing. The list_houses pointer in the slug param is the only routing signal.

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 usefully discloses one runtime behavior — lat/lng are null when coordinates are unresolved — which is exactly the kind of surprise an agent needs. It says nothing about permissions/auth, what happens for an unknown slug, or whether the AI 設計提案 field is costly to compute.

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

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

Two compact sentences with zero filler: the returned content first, the null-coordinate caveat second. Nothing is repeated and nothing is buried.

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 does the right thing by enumerating the returned fields and flagging the nullable pair. For a single-parameter read tool this is close to sufficient; only auth/error behavior is missing.

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

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

Schema coverage is 100% and the single parameter's description already points to list_land_listings for obtaining a slug. The description only restates 「slug を指定して」, adding no format or sourcing detail beyond the schema, so baseline 3 applies.

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

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

States a specific verb (取得) and resource (1件の売地の詳細) and enumerates the content returned (価格・面積・用途地域・AI 設計提案・座標). It doesn't name list_land_listings as the sibling it complements, but the singular-vs-list distinction is clear from the text.

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

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

The phrase 「slug を指定して 1 件」 implies this is the single-record lookup, but the description never states when to use it instead of list_land_listings or probe_land. Routing to the listing tool appears only in the schema's parameter description, not in the tool description itself.

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 behavioral burden. '取得' implies a read-only retrieval and the parenthetical lists returned fields, which adds useful context, but permissions, not-found behavior, and rate limits are not disclosed.

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?

A single front-loaded sentence with no wasted clauses. The action, input condition, and key returned fields are all stated efficiently.

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

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

For a simple single-SKU lookup with no output schema, the description adequately covers purpose, input, and returned fields. It still omits edge-case behavior such as what happens when the SKU is not found.

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?

There is one parameter and schema description coverage is 100%, so the schema already documents 'sku'. The description reinforces that SKU selects the product but adds no format or constraint 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?

States a specific verb/resource: retrieve one product's details by SKU, with representative fields listed. It is clear what the tool does, but it does not explicitly distinguish itself from sibling search_catalog or other product 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 condition 'SKU を指定して' implies it should be used when the SKU is known and a single product detail is needed. However, it gives no explicit when-not guidance or alternatives such as search_catalog when the SKU is unknown.

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 behavioral burden. It does disclose that the tool returns a pass/fail (合否) from houki-engine, but says nothing about permissions, what data the slug must resolve to, failure modes, or whether the check is read-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?

One efficient sentence with the verb and result form front-loaded and the checked items enumerated. No filler, though the enumeration is dense enough to approach the limit of usefulness.

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 tool with no output schema, the description covers what is checked and that pass/fail is returned. It leaves open what the slug must reference and what a failure result contains, so it is adequate but not complete.

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

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

There is a single parameter with 100% schema description coverage (物件 slug), so the schema already documents it. The description adds no meaning about what slug refers to or where it comes from, which is the baseline 3 case.

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

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

States a specific verb (実行し合否を返す) and resource (建築基準法チェック), and enumerates the actual checks performed (建ぺい率・容積率・斜線・採光・換気), so the agent knows precisely what it does. It does not differentiate from plausible siblings like build_on_land, which is why it stops short of 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?

Usage is implied: run a building-code compliance check against a property. There is no explicit when-to-use / when-not-to-use guidance and no mention of alternatives such as build_on_land, so the agent must infer selection.

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

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

Since there are no annotations, the description carries the burden of disclosure. It adds crucial behavioral context by defining *what* the output contains (slug, scale, BIM completeness %) and *what* the data originates from (curated vs. user-created).

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 highly efficient. It front-loads the core purpose, clearly states the output fields, and immediately follows with the critical scope constraints (default exclusion/inclusion), maximizing information per 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?

Given that the tool lists properties with specific attributes (scale, BIM completeness), the description is highly complete. It tells the agent exactly what kind of data set it is operating on, which is essential for decision-making.

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?

Although parameter coverage is 100%, the description adds vital semantic meaning by linking the `include_user` boolean not just to a technical toggle, but to the difference between 'curated' properties and 'user-created' properties.

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 its purpose: to list curated public properties (famous buildings/landmarks). It immediately defines the resource and its scope, distinguishing it from potentially broader or user-focused listing 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?

It provides explicit instructions on default behavior (excluding user-created properties) and the exact mechanism (`include_user=true`) needed to override that default and include user-generated content.

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

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

No annotations are provided, so the description must carry behavioral context. It usefully discloses the return contents (price, area, zoning, link, geocoded coordinates) and data source, but says nothing about ordering, pagination beyond the limit param, or freshness beyond 'SUUMO 実値ベース'.

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?

Three compact sentences, front-loaded with what it returns, then filters, then the map-data equivalence. Little waste; only mildly dense.

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 list tool with all-optional params and no output schema, enumerating the returned fields is the key completeness marker, and it is present. Minor gaps in ordering/pagination are tolerable.

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 params are already documented. The description lists three of the four filters and restates the q matching behavior, but omits the limit param and adds no format or syntax detail beyond the schema—so baseline 3 applies.

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

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

States a specific verb-resource pair (return a list of currently-for-sale land) and adds the data source (SUUMO actual values). The plural 'list' implicitly distinguishes it from the singular get_land_listing sibling, though no sibling is named explicitly.

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 is implied by 'currently for sale' and the filter list, and it notes the data matches the orange pins on the /earth map. However, it never explicitly says when to use this vs get_land_listing or list_houses, 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?

With no annotations, the description carries the burden, and it does add one genuinely useful behavioral fact: an Authorization Bearer API key is mandatory. It does not disclose whether results are paginated, sorted, or whether an empty list is returned when the account owns nothing.

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

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

Two compact sentences with the core behavior first and the auth prerequisite second. No filler, though the auth sentence could be folded in more tightly.

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 no-parameter read tool this covers what it returns and the auth requirement, but with no output schema the description could say more about the shape of the returned product entries or result limits. Adequate but leaves the agent guessing about return 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 tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The schema is empty and fully consistent with the description.

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

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

States a specific verb+resource: returns the list of products registered by the calling account (the API key's account). This distinguishes it from list_houses/list_land_listings by resource type, though the name 'list_mine' alone would be ambiguous without the description.

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?

Implicit guidance only: an agent can infer it should call this when it wants the caller's own products rather than catalog-wide results. No explicit when-not guidance or pointer to search_catalog/get_product for other lookups.

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 disclosure burden. It does a good job describing what is returned (BOM, total, ㎡単価, lead_time_days, inventory, critical-path delivery date), but it never says whether the call is read-only, whether it is expensive/slow, whether it mutates or caches anything, or what precondition failures look like.

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

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

One dense sentence that front-loads the core purpose (カタログ連携の概算見積もり) and then enumerates inputs and outputs. No filler, though the packed clause about prices and 原単位 takes some parsing.

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 — and it does, naming BOM, total, ㎡単価, per-material lead_time_days, inventory, and critical-path delivery date. Combined with the trivial single-parameter schema, an agent has enough to call it correctly.

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

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

The single parameter 'slug' has full schema description coverage ('物件 slug'), so the schema already does the work and baseline 3 applies. The description adds no additional meaning about the slug, such as which property listing it must reference or whether it comes from list_houses.

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

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

States a specific verb and resource: computes a rough quote (概算見積もり) as BOM, total cost, and per-㎡ unit price from BIM takeoff plus catalog prices. The catalog/BIM inputs distinguish it from siblings like search_catalog or get_house_bim, though it never explicitly names those siblings as alternatives.

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

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

Usage is only implied: an agent infers it should call this when a costed BOM is needed for a property. There is no explicit when-to-use, no exclusion of the catalog/house tools, and no stated prerequisite (e.g., that the house must already have BIM data) before invoking it.

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 there are no annotations, the description must provide full behavioral context. It explains that the results are a 5-axis score and that the inclusion of the `zoning` parameter specifically alters the internal logic regarding the legal score calculation, which is a crucial 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 concise, using two primary sentences to cover the core functionality, the variable input behavior, and the external context (map functionality). There is zero unnecessary language.

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 that there is no output schema, the description provides maximum context by defining the nature of the output (a Site IQ score across 5 specific dimensions). This allows the agent to fully anticipate the type of information 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?

While schema coverage is 100%, the description adds significant value by providing examples of valid zoning codes (low1, res1, shop) and explaining the functional necessity of the parameter—it's required specifically to 'recalculate' the legal score.

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 is highly specific, stating it scores land based on 'Site IQ' and explicitly enumerating the five scoring axes (topography, solar radiation, disaster risk, legal headroom, climate). This leaves no doubt about the tool's core function.

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 operational guideline regarding the `zoning` parameter: providing a zoning code triggers a recalculation of the legal score. This dictates how the user should utilize the optional input parameter to achieve different results.

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 and does well: it discloses that this is a soft retirement, not a hard delete (ハード削除はしない), that a Bearer API key is mandatory, and that ownership restricts the operation. It does not say whether retirement can be reversed or what happens to listings that reference the SKU.

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?

Three compact clauses: action plus effect first, then auth, then eligibility restriction. Nothing is padded and the most decision-relevant fact (retire, not delete) 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?

Covers the essential decision inputs for a destructive-ish mutation: what it does, that it is soft, auth requirements, and eligibility. Without an output schema, the description could still note reversibility and expected response, which is the only remaining gap for a one-parameter 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?

A single parameter (sku) with 100% schema description coverage, so the schema already defines it as the SKU to retire. The description adds only the ownership restriction on that argument (own vs others'/official), which is useful but minimal; baseline 3 applies.

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

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

Names a specific verb (取り下げる/retire) and resource (製品/product), and narrows scope to products the caller registered themselves (自分が登録した製品). It also disambiguates the effect from deletion (ハード削除はしない), but never contrasts the action with siblings like update_product or set_visibility, so the boundary with those tools must be inferred.

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 an explicit exclusion: 他者/公式 SKU は不可 (other users' or official SKUs cannot be retired), which tells the agent when not to call it. It also states the auth prerequisite. It stops short of naming the alternative tool to use when a SKU is not one's own, or when the intent is to change visibility rather than retire.

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 supplied, so the description carries the full disclosure burden. It does convey useful scale context (3,900+ SKU), which implies large candidate result sets and motivates the limit parameter, but it says nothing about read-only nature, ordering/ranking of matches, pagination beyond the limit cap, or what a result record contains.

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

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

Two compact sentences that front-load the resource and scale, then the filter facets. Nothing is repeated from the schema and no sentence is filler.

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

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

There is no output schema and no annotations, so the description ideally would say what comes back (e.g. product IDs usable with get_product) — that is the remaining gap. Given all parameters are optional and fully documented in the schema, the definition is otherwise sufficient to invoke the tool correctly.

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

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

Schema description coverage is 100%, so all four parameters are already documented with match semantics (部分一致 for q, 完全一致 for brand/category) and examples. The description names three of the facets but adds no matching-behavior or combination detail beyond the schema; baseline 3 applies.

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

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

States a specific verb (検索) and resource (bim.house の建材・設備カタログ), and adds scope details an agent can act on: 3,900+ SKU and the filterable facets (brand/category/keyword). It does not explicitly distinguish itself from the closest sibling, get_product, which presumably retrieves a single item by identifier, 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?

Usage is only implied: an agent can infer this is the browse/discovery entry point and get_product is the by-ID lookup, but the description never says when to choose this over that, nor whether filters are combinable or what to do when zero results return. No explicit exclusions or prerequisites 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?

With no annotations, the description carries full burden. It usefully discloses the edit_token precondition and the meaningful behavior that unlisting keeps the direct link alive, but omits reversibility, permission requirements, and response shape.

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?

Compact and front-loaded: the toggling action and required token lead, followed by the private semantics and use case. Every sentence contributes without padding.

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 three-param toggle with full schema coverage and no output schema, the description covers prerequisites, toggle semantics, and intended use. Reasonably complete, with only minor gaps in reversibility and permissions.

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 a 3 baseline applies. The description adds value beyond the schema by naming the edit_token's origin (create_house return value) and restating the private toggle semantics, aiding correct invocation.

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

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

States a specific verb (toggle listing/non-listing) with a clear resource (property) and disambiguates the mechanism: private=true hides it from the listing but the direct link remains. This distinguishes it from a delete/retire operation, though no sibling is named explicitly.

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?

Gives a concrete when-to-use example ('culling low-score properties in the evolution loop, etc.'), but offers no explicit exclusions or named alternatives such as retire_product, so the agent must infer when not to use it.

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 zero annotations the description carries the whole burden and does disclose the key behavioral facts: Bearer API-key auth is mandatory, ownership is enforced, and the update is a partial patch ("指定したフィールドのみ上書き"). It omits error/response behavior and whether overwrites are reversible.

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?

Three short sentences, no filler, with the ownership constraint and auth requirement front-loaded before the merge behavior. Every clause adds information.

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

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

For a 17-parameter mutation with no annotations and no output schema, the description covers auth, ownership and patch semantics but leaves field-level meaning and failure behavior unexplained. Adequate to avoid misuse, not complete enough to call correctly with confidence.

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 18% across 17 parameters, so the description must compensate and it largely does not. The partial-update note is genuinely useful, but the 16 optional fields (tags, spec, stock_status enums, price_jpy units, etc.) get no explanation of format or merge-vs-replace semantics beyond "上書き".

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

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

States a specific verb+resource (updates product fields) and anchors it to provenance: only products the caller registered via create_product. That framing cleanly separates it from create_product, get_product and retire_product in the sibling list.

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

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

Explicitly names the exclusion condition (other people's products and official SKUs cannot be updated) and implies the create_product prerequisite. It stops short of naming an alternative for the read path (get_product) or stating what to do when the update is rejected.

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 burden and does well: it discloses the auth prerequisite (Bearer token obtained at /console) and the returned value (email). It omits failure behavior (what happens with an invalid/missing key) and any rate limits, keeping it short of a 5.

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?

Three short sentences, front-loaded with the purpose and followed by the auth requirement and return value. The closing 'Web/CLI どちらからでも使える' is marginally useful context rather than essential information, but nothing is padded.

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 zero-parameter, annotation-free tool with no output schema, the description covers purpose, auth mechanism, and return value — enough to call it correctly. Only error/edge-case behavior is missing, 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?

The tool takes zero parameters, so the baseline is 4. The description correctly adds no parameter detail and instead spends its words on the auth header, which is the only input-like information relevant here.

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?

Names a specific operation (API key authentication check) and its concrete result (the authenticated account's email). No sibling tool does anything similar, so the agent can distinguish it at a glance.

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?

Explains how to invoke it for its purpose — attach 'Authorization: Bearer <API key>' issued at /console — and notes it works from Web or CLI. It gives clear context but does not name alternatives or say when not to use it.

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