Skip to main content
Glama

HORIZON SHIELD YAKUMO (verified contractor directory)

by io.github.ogasurfproject-jpg

検証の仕組み

how_verification_works
Read-onlyIdempotent

Yakumo の掲載審査(KIRA適正診断)がどう機能するかを返す。適正価格の検証・過剰請求の赤旗検出・適正度スコアと誠実度ティア・再計算できる署名レシート(SHA-256)・掲載後の継続監視・fail-closed(通らない店は施主向けに一切出さない)・中立(紹介料なし)。施主が『検証済み』の意味を理解するための説明。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

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

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description goes beyond by detailing the content of the explanation (red flags, score tiers, SHA-256 receipt, continuous monitoring, fail-closed behavior, neutrality), which is valuable behavioral context. No contradictions with annotations.

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 a single, information-dense sentence that lists all key aspects of the verification mechanism without extraneous words. It is front-loaded with the primary purpose ('掲載審査がどう機能するかを返す') and efficiently enumerates the features. No waste.

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?

Since there is an output schema (though not shown, it exists), and this tool has no parameters amplifying complexity, the description fully captures the tool's role: explaining verification mechanics to homeowners. It covers the key features, making it complete for both selection and invocation. The output schema presumably provides return structure, so the description need not reiterate.

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?

There are zero parameters, so description doesn't need to document them. The schema coverage is 100% (vacuously). The description provides meaning about what the tool returns, which is the core semantic information for a parameterless info tool. Baseline 4 for 0 params is appropriate.

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 states it returns an explanation of how Yakumo's listing review (KIRA appropriateness diagnosis) functions, listing specific features like price verification, red-flag detection, scoring tiers, receipts, monitoring, fail-closed behavior, and neutrality. This distinguishes it from sibling tools that list or profile stores, as it is about the verification mechanism itself.

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

Usage Guidelines3/5

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

The description implies usage for helping homeowners understand what 'verified' means, but it does not explicitly state when to use this tool versus sibling tools or what prerequisites exist. There is no explicit when-not-to-use guidance, though the informational nature is clear. It provides some context but lacks explicit alternative recommendations.

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