Skip to main content
Glama

HORIZON SHIELD YAKUMO (verified contractor directory)

by io.github.ogasurfproject-jpg

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
NameRequiredDescriptionDefault
needYes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
NameRequiredDescriptionDefault
roster_readNotrue = 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_countNo
roster_sourceNo
verified_countNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • 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"
+  }
+}
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "type": "object"
+}
  3. First observed

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) toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation4/5

The tools are mostly distinct: check_named_contractor handles specific named contractors, find_contractor handles free-text searches, get_contractor_profile retrieves a single profile, list_verified_stores lists stores, mall_overview gives an overview, and how_verification_works explains the process. There is slight overlap between find_contractor and list_verified_stores (both return verified stores), but the former is a natural-language command tower while the latter is a direct filterable list, so the boundary is clear enough.

Naming Consistency4/5

Most tools follow a verb_noun pattern: check_named_contractor, find_contractor, get_contractor_profile, list_verified_stores, mall_overview. The exception is how_verification_works, which uses a question-like phrase rather than a verb_noun structure, but it is still readable and consistent in style. Overall, the naming is predictable and clear.

Tool Count5/5

With 6 tools, the server is well-scoped for its purpose: a verified contractor directory. Each tool serves a distinct function: checking a named contractor, finding contractors, viewing profiles, listing stores, explaining verification, and providing an overview. No tool feels redundant or missing; the count is appropriate for the domain.

Completeness4/5

The tool surface covers the core workflows: searching, listing, profiling, and explaining the verification process. However, there is no tool for submitting a contractor for verification or for updating store information, which might be expected in a directory that manages verified stores. That said, the server appears to be consumer-facing (for homeowners), so those gaps are acceptable and agents can work around them by directing users to the mall links.

Resources