HORIZON SHIELD YAKUMO (verified contractor directory)

検証済みの職人を探す(司令塔)

find_contractor

Read-onlyIdempotent

施主の相談文(自由記述)から Yakumo の検証済み加盟店を探す司令塔。need(例:『愛知県で外壁塗装できる信頼できる業者』)を渡すと地域と工種を推定し、検証を通過した店を返す。該当が無ければ相場(souba)や無料の第三者チェック(EHN)への導線を返す。金額は返さない(スコア・ティアのみ)。紹介料なし・verified-first・Japan only。

Input Schema

TableJSON Schema

Name	Required	Description	Default
`need`	Yes	探している内容(日本語自由記述)。例: 神奈川で屋根の雨漏り修理、長久手で内装リフォーム

Output Schema

TableJSON Schema

Name	Required	Description
`roster_read`	No	true = the contractor roster was read successfully; any counts below are real facts about the roster. false = the roster could NOT be read, and this response makes no claim about how many contractors exist. A count of 0 with roster_read true means nobody matched. There is no case where a failed read reports a count.
`pending_count`	No
`roster_source`	No
`verified_count`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedAug 20, 2026

addedOutput schema / properties

Added value: +{
+  "pending_count": {
+    "type": "number"
+  },
+  "roster_read": {
+    "description": "true = the contractor roster was read successfully; any counts below are real facts about the roster. false = the roster could NOT be read, and this response makes no claim about how many contractors exist. A count of 0 with roster_read true means nobody matched. There is no case where a failed read reports a count.",
+    "type": "boolean"
+  },
+  "roster_source": {
+    "enum": [
+      "kv",
+      "published",
+      "none"
+    ],
+    "type": "string"
+  },
+  "verified_count": {
+    "type": "number"
+  }
+}

Changed1 schema field changedJul 19, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "type": "object"
+}

First observedJul 19, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses key behaviors: it estimates region and trade, returns only verified stores, does not return prices (only score/tier), and provides fallback guidance. It also states business constraints (no referral fee, verified-first, Japan only), giving agents a rich picture of what to expect.

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

Conciseness5/5

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

The description is well-structured and front-loaded, starting with the purpose and then adding behavioral details and constraints. Every sentence contributes useful information without redundancy or unnecessary length.

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

Completeness5/5

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

With one parameter, a rich output schema, and strong annotations, the description covers the essential operational aspects: input format, matching behavior, fallback paths, and output limitations. It is complete for an AI agent to select and invoke the tool appropriately.

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

Parameters4/5

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

The schema already covers the single 'need' parameter with examples, so the baseline is 3. The description adds semantic value by explaining that 'need' should contain a free-form Japanese request and that the tool will infer region and trade from it, which helps the agent formulate the parameter correctly.

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

Purpose5/5

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

The description clearly identifies the tool as a '司令塔' (command center) that searches Yakumo verified contractors from free-form client requests, which is a specific verb+resource pairing. It also distinguishes itself from siblings like check_named_contractor and list_verified_stores by emphasizing free-form consultation text and verification-first matching.

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

Usage Guidelines4/5

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

The description provides clear context for when to use the tool: pass a free-form 'need' and the tool infers region and trade. It mentions fallback paths (souba and EHN) when no match exists, but it does not explicitly list exclusions or name sibling alternatives for when not to use this tool.

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

All HORIZON SHIELD YAKUMO (verified contractor directory) tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.