補助・助成.jp

使える補助金を探す

recommend_subsidies

Read-only

【最初に使う】自社に合う補助金候補を探し、判定済みの一覧を返す。通常は引数なしで呼ぶ。

    プロフィールの search_keywords で検索し、地域・募集期間・従業員数で足切りした上で、
    上位 detail_top_n 件は詳細を取得して一次判定する（初回は数十秒かかる）。
    review_scope は要領の抽出範囲と未確認項目、checks は省略していない根拠。抽出済みは全要件確認済みではない。
    各候補: status（likely_eligible / needs_review）、acceptance_phase、deadline、days_left、estimated_yen（補助額試算）、
    acceptance_phase が unknown の候補は、Jグランツの受付期間が新規応募のものか確かめられていない（deadline は null）。
    新規応募の締切を公式サイトで確認してから案内する。
    concerns（要確認点。「要領 p.N」は根拠ページ）、url。
    local がある場合は所在地に該当する自治体・支援機関の制度（内容と要件はリンク先で確認）。報告時は source の出典表記を添える。
    keywords を渡すとプロフィールのキーワードの代わりに使う（2文字以上の短い語。40個・1語30文字まで）。
    detail_top_n は10まで。
    無料プランの利用者には、公募要領・詳細は読まない一覧だけを返す（detail_top_n は使わない）。結果の plan に残りの回数と案内がある。
    purposes を渡すと、その目的（どれか）の制度に絞る（例: 「IT導入の支援を探して」→ ["IT・DX"]）。
    国・自治体の制度・新着で同じ分類を使う。絞った場合は purpose_note の注意を添えて報告する。

Input Schema

Name	Required	Description	Default
`limit`	No
`keywords`	No
`purposes`	No
`detail_top_n`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 21, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Despite annotations already covering read-only and open-world, the description adds substantial non-obvious behavior: first-call latency of tens of seconds, a free-plan mode that skips guideline reading and ignores detail_top_n, the plan field carrying remaining quota, the meaning of review_scope/checks, and that estimated_yen is only a 試算. It also flags the unknown-acceptance-phase edge case where deadline is null and must be verified on the official site.

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?

Front-loaded with the use-first marker and the no-argument default, and nearly every sentence carries operational content. It is dense but somewhat disorganized: per-parameter guidance (keywords, detail_top_n, purposes) is scattered after output-field explanations and the purposes note arrives last instead of grouped with the other parameters.

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?

For a complex, open-world, quota-limited discovery tool this covers what an agent needs to call and interpret it: invocation pattern, cost/latency, plan gating, candidate status vocabulary, null-deadline handling, source attribution for local entries, and the caution note required when purposes filtering is applied. Return values are also covered by an output schema, so the field explanations are bonus context rather than a gap-filler.

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 0%, so the description must compensate and largely does: keywords have length/count limits (2+ chars, max 40 items, 30 chars each) and an explicit override semantic vs. profile keywords; purposes is illustrated with a concrete example mapping; detail_top_n has a cap of 10. Only `limit` (default 20) is left entirely undocumented.

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

Purpose4/5

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

States a specific verb+resource: search for subsidy candidates matching the company and return a pre-judged list (判定済みの一覧). The 「判定済み」 framing implicitly separates it from the raw search_subsidies sibling, but no sibling is named explicitly, so differentiation is inferred rather than stated.

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?

「【最初に使う】」 and 「通常は引数なしで呼ぶ」 give clear entry-point context and a default invocation pattern; the purposes/keywords paragraphs explain the optional narrowing paths. However, it never states when NOT to use it or names search_subsidies / check_eligibility / check_new_subsidies as the alternative for a different intent.

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

All 補助・助成.jp 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.

Resources

Need Help?