[EN] Create a DRAFT purchase order for one trade of a house to a contractor (does NOT send anything — human sends later). / 物件の1工種を業者へ発注 (ドラフト作成のみ・⚠送信はしない)。spec/検査リストを同梱。
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | 物件 slug | |
| trade | Yes | 工種 code (get_build_plan の phases.trade) | |
| contractor_id | Yes | match_contractors / list_contractors の contractor_id |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses key trait: does NOT send, only drafts. Also mentions inclusion of spec/inspection list. Does not cover auth, rate limits, or side effects, but for a draft-creation tool, the essential behavior is well communicated.
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 key action and constraint. Bilingual version efficient. No wasted words; every part adds 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?
No output schema, but description states draft creation and human action later. Could mention return value (e.g., order ID) but not essential for basic usage. For a simple 3-param tool, it's nearly 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 coverage is 100%, baseline 3. Description adds value by indicating sources: trade code from get_build_plan phases.trade, contractor_id from match_contractors/list_contractors. This helps agent fetch correct values, exceeding mere schema repetition.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb (create), resource (DRAFT purchase order), scope (for one trade of a house to a contractor), and distinguishes from sending by explicitly noting draft-only. Sibling tools include creation tools but none for orders, so purpose is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Context is clear: use for draft orders only, and human sends later. However, no explicit when-not-to-use or alternative tools mentioned. The sibling list includes 'material_quote' which might be related, but no direct comparison.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have distinct purposes, but some potential overlap exists (e.g., get_site_context and get_houki_rules both provide site conditions, and set_site_context vs. upsert_zoning_rule could be confused). Overall, descriptions help disambiguate.
Tools predominantly use a verb_noun pattern (e.g., create_house, update_house, set_visibility). A few outliers like houki_check and whoami break the pattern, but naming is mostly consistent.
29 tools is heavy but covers a broad domain (house design, construction, catalog, contractors, admin). Some tools are niche (e.g., list_incomplete_addresses, set_forkable), but each serves a clear purpose. Could be streamlined.
Core operations for house lifecycle (create, read, update, check) are present. Lacks explicit delete/archive for houses (only set_visibility), and no tool to update site context directly (only set via set_site_context). Minor gaps but domain is well-covered.