Skip to main content
Glama

HORIZON SHIELD: Construction Estimate Auditor for Japan (KIRA)

by io.github.ogasurfproject-jpg

注意喚起の発信下書き

draft_broadcast
Read-onlyIdempotent

ある工事の過剰請求への注意喚起を発信する下書き(note用長文・X用短文)を生成し、HORIZON SHIELDの該当解説ページ(実在URL)への被リンクを添える。価格はKIRA(検証可能SHA-256付き)の一次データのみ。推測の数字は入れない。下書きであり公開前に運営者が最終版にする(自動投稿しない)。 / Generates broadcast DRAFTS with backlinks. Verifiable first-party prices only. Draft; operator finalizes. No auto-posting. USE WHEN: the operator wants note/X draft text warning about overcharging for a given work type. DO NOT USE WHEN: the caller wants a verdict on a specific quote (call intake_estimate) or the tactic list itself (call scan_tactics). Output is a DRAFT for a human to finalise. This tool never posts.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
workYes工事名やキーワード(日本語)。例: 外壁塗装, トイレ, 火災保険

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYesWhether a draft was produced.
noticeNoThis is a DRAFT. A human finalises it. Nothing is posted.
sourceNoWhich server produced this.
post_targetsNoPer-channel draft text (note long form, X short form) with backlinks.
price_sourceNoWhich first-party data any figure in the draft came from.

Schema Changelog

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

  1. Changed2 schema fields changed
    • addedOutput schema / properties
      Added value: +{
+  "notice": {
+    "description": "This is a DRAFT. A human finalises it. Nothing is posted.",
+    "type": "string"
+  },
+  "ok": {
+    "description": "Whether a draft was produced.",
+    "type": "boolean"
+  },
+  "post_targets": {
+    "description": "Per-channel draft text (note long form, X short form) with backlinks.",
+    "items": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "price_source": {
+    "description": "Which first-party data any figure in the draft came from.",
+    "type": "string"
+  },
+  "source": {
+    "description": "Which server produced this.",
+    "type": "string"
+  }
+}
    • addedOutput schema / required
      Added value: +[
+  "ok"
+]
  2. Changed2 schema fields changed
    • changedInput schema / properties / work / description
      Previous value: -"工事名やキーワード(日本語)。例: 外壁塗装, トイレ, シロアリ, 食洗機, 火災保険"New value: +"工事名やキーワード(日本語)。例: 外壁塗装, トイレ, 火災保険"
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "type": "object"
+}
  3. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the bar is lowered. The description adds valuable context: drafts are for operator finalization, no auto-posting, only KIRA-verified prices are used, and speculation is forbidden. No contradictions found.

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 with a Japanese/English bilingual summary, followed by clear usage guidelines. Every sentence serves a purpose: stating output, constraints, and exclusions. No wasted words.

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?

Given the tool has one required parameter, an output schema, and clear annotations, the description covers all necessary context: when to use, when not to use, what the draft contains, and behavioral guarantees. It is fully adequate for an agent to select and invoke this tool correctly.

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?

Schema coverage is 100% and the schema describes the 'work' parameter as a Japanese work name/keyword with examples. The description adds context by explaining the purpose of this parameter in generating warnings about overcharging, but does not extensively elaborate beyond what the schema already conveys.

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 states the tool generates broadcast drafts (note/X) with backlinks using verifiable first-party prices only. It clearly distinguishes itself from siblings like intake_estimate and scan_ttactics by specifying it does not post automatically and only produces drafts.

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

Usage Guidelines5/5

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

The description explicitly states 'USE WHEN' for warning about overcharging and 'DO NOT USE WHEN' for verdict on quotes or tactic lists, naming sibling tools as alternatives. This provides clear guidance on when to choose this tool over others.

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

All HORIZON SHIELD: Construction Estimate Auditor for Japan (KIRA) 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

A4.7/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: draft_broadcast generates text, intake_estimate provides price verdicts, scan_tactics returns awareness material, route_request is a deterministic router, and run_full_audit orchestrates the others. The USE WHEN / DO NOT USE WHEN clauses explicitly delineate boundaries, leaving no ambiguity.

Naming Consistency5/5

All five tools follow a consistent verb_noun snake_case pattern (draft_broadcast, intake_estimate, route_request, run_full_audit, scan_tactics). The verbs and nouns clearly describe the action and object, with no mixing of conventions or vague terms.

Tool Count5/5

Five tools is a well-scoped number for this service: a router, two specialized analysis tools, a draft generator, and an orchestrator. Each tool has a clear role and earns its place, with no redundancy or excessive bloat.

Completeness5/5

The surface covers the full workflow: intake, tactics, broadcast drafting, and orchestration, plus a router that handles edge cases (outside Japan, non-construction, emergencies). The router ensures no dead ends by directing users to appropriate external resources, and all core use cases are addressed.

Resources