Skip to main content
Glama

HORIZON SHIELD

by dev.workers.oga-surf-project.hs-mcp
This connector has been deprecated

Superseded by the io.github.ogasurfproject-jpg/horizon-shield listing at https://mcp.horizonshield.dev, which is the URL published in the official MCP registry. The endpoint behind this listing is the same server and stays reachable.

Audit Estimate Against Fair Price

audit_estimate
Read-only

業者が提示した見積金額が適正かを、HORIZON SHIELDの適正レンジ(souba-db, 大賀俊勝 実務監修)と照合して判定する。手元に具体的な見積額がある時に使う。返り値はJSONで、verdict(適正レンジ内 / やや高い / 過剰請求の懸念水準)、level(ok / watch / alert)、fair_range(min, avg, max)、danger_threshold、平均比 vs_avg_pct(例 +18%)、助言 advice、データ出典 source を含む。工事名が見つからない場合、近い候補があれば did_you_mean として返す。単価(平米など)建ての工事に総額らしい金額を渡した場合は unit_mismatch の案内を返す。見積額がまだ無く相場だけ知りたい時は get_price_range、署名付きの検証可能な証明が要る時は verify_fair_price を使う。Japan only, JPY。 / Audits whether a contractor quoted price for a Japanese construction or renovation job is fair by comparing it against HORIZON SHIELD fair-price ranges (souba-db). Use when the user already has a specific quoted amount. Returns a JSON object with verdict, level (ok, watch, alert), fair_range (min, avg, max), danger_threshold, percentage gap versus the average (vs_avg_pct, e.g. +18%), advice, and data source. If the work name has no match, close candidates may be returned as did_you_mean. If the work is priced per unit and the amount looks like a total, a unit_mismatch notice is returned instead. For the typical range only use get_price_range; for a signed verifiable attestation use verify_fair_price.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
workYes工事名(日本語)。材料やグレード込みで具体的に。例: 外壁塗装 シリコン。部分一致で照合するため曖昧だと別カテゴリにヒットしやすい。未マッチ時は近い候補が did_you_mean で返ることがある。
quoted_priceYes業者提示の金額(円, 数値)。一式見積はその総額。税込/税抜は正規化せず、渡した数値をそのまま適正レンジと照合する。

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNoHow many records matched. 0 means the source was read and nothing matched. It never means the source could not be read, that returns isError: true.
levelNook / watch / alert
adviceNo助言
lookupNook = the source was read and something matched. absent = the source was read and nothing matched. A source that could NOT be read never appears here: that returns isError: true and makes no claim about what does or does not exist.
verdictNo判定
fair_rangeNomin/avg/max
vs_avg_pctNo平均比(例 +18%)
source_readNotrue on every successful result. A failed lookup does not return a result at all, so this is never false, it is declared so a consumer can assert on it.
did_you_meanNoNear matches, when an exact match was not found.

TDQS

A4.8/5.0
Behavior5/5

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

Even though annotations already mark it as readOnly and non-destructive, the description adds significant behavioral details: it explains partial matching behavior, the did_you_mean response for unmatched work names, and unit_mismatch handling for per-unit vs total amounts. This goes beyond the annotations to inform the agent about edge cases.

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

Conciseness4/5

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

The description is thorough but not overly verbose. It includes necessary details about return fields, edge cases, and usage alternatives in a structured manner. The bilingual format adds length but each part contributes to clarity. It earns a high score for being informative without redundancy.

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 output schema exists, the description still explains all return fields (verdict, level, fair_range, danger_threshold, vs_avg_pct, advice, source) and additional response cases (did_you_mean, unit_mismatch). It also provides the geographic and currency context, making the tool's behavior fully understandable.

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%, so baseline is 3. The description enhances parameter understanding by specifying that 'work' should be in Japanese, providing an example, mentioning partial matching, and clarifying that 'quoted_price' is a total amount without normalization. This adds meaningful context beyond the schema.

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 the tool's purpose: to audit a quoted price against a fair range, using specific verbs like 'audits' and 'comparing'. It distinguishes from sibling tools by explicitly naming alternatives (get_price_range, verify_fair_price) and their appropriate use cases.

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?

Guidelines are explicit: 'Use when the user already has a specific quoted amount' and 'For the typical range only use get_price_range' clearly indicate when to use this tool versus alternatives. It also mentions the context of Japan and JPY, providing clear usage boundaries.

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

All HORIZON SHIELD 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

A4.1/5.0
Disambiguation4/5

Most tools have distinct purposes: audit_estimate for detailed quote diagnosis, get_price_range for typical ranges, preview_reverse_estimate for early-stage direction, verify_fair_price for tamper-evident records. However, audit_estimate, get_price_range, and preview_reverse_estimate overlap in the price-checking domain, and verify_fair_price vs verify_integrity_claim could be confused (both involve SHA-256 verification), though descriptions clarify the opposite postures.

Naming Consistency4/5

Most tools follow a verb_noun pattern (audit_estimate, check_red_flags, get_price_range, list_cost_categories, search_cost_category, suggest_ehn, verify_fair_price). Minor deviations: create_ap2_fairness_attestation is longer and more specific, and get_agent_card/get_estimate_reading_guide/get_fair_price_sources/get_jccdb_dataset_info all start with 'get' but vary in noun phrasing. Overall consistent and predictable.

Tool Count4/5

14 tools is within the ideal 3-15 range, and each tool serves a distinct function in the domain of construction estimate auditing and fair-price verification. Slightly on the higher end but justified by the breadth of features (price lookup, audit, attestation, verification, data sources, educational guides).

Completeness4/5

The server covers the core workflow: lookup price ranges, audit specific quotes, check red flags, generate attestations, verify claims, and access data sources. Minor gaps: no tool for submitting new price data or updating categories, and no direct tool for comparing multiple quotes side-by-side, but agents can work around these with existing tools.

Resources