搜尋政府標案公告。
q: 關鍵字（比對標題與機關名，例「冷氣」「智慧路燈」）。
kind: tender=招標中 / award=已決標 / failed=流標，空=全部。
region: 縣市（例「台北市」「高雄市」，「臺」寫成「台」）。
year: 西元年（例 2026）。
unit_id: 機關代碼（用 find_entity 取得）——查「某機關發的案」用這個，
比 q 精確（q 是全文比對）。
vendor: 廠商名稱（正式全名）——查該廠商投標／得標過的案。
budget_min/budget_max: 預算金額範圍（新台幣元）。
回傳最新 10 筆與總數；需要更多用 page 翻頁。
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | ||
| kind | No | ||
| page | No | ||
| year | No | ||
| region | No | ||
| vendor | No | ||
| unit_id | No | ||
| budget_max | No | ||
| budget_min | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
無 annotations，描述承擔行為揭露責任。說明回傳「最新 10 筆與總數」及分頁機制，提供實際調用後的行為預期。雖未明說為唯讀操作，但由搜尋語意可合理推斷。
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
以條列式逐一說明參數，每行簡潔且資訊密度高，最後補充分頁行為，無冗詞，結構易於掃讀。
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
9 個參數全數解釋，包含格式、範例及用途；同時說明回傳內容與分頁，無輸出 schema 的情況下已提供足夠資訊，使 agent 能正確呼叫。
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
schema_description_coverage 為 0%，描述完全補償，對每個參數（q、kind、region、year、unit_id、vendor、budget_min/max）都給出具體語意與範例，讓 agent 能正確填值。
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
描述明确說明「搜尋政府標案公告」，動詞+資源清晰。但未明確與兄弟工具（如 get_tender、find_entity）區分，不過本身功能已足以辨識。
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
描述詳細說明每個參數的使用情境，例如 unit_id 用於查某機關的案且比 q 精確、vendor 查廠商投標紀錄，提供清晰的上下文與選擇依據。但未明確提及何時不該用此工具或替代工具，故未滿分。
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: search, entity lookup, tender detail, price analysis, vendor/unit reports, head-to-head comparison, and hot opportunities. Even similar-sounding vendor_report and compare_vendors are unambiguously different in scope.
Naming is mixed: some tools use verb_noun (search_tenders, find_entity, get_tender, compare_vendors) while others use noun_noun or adjective_noun (unit_report, vendor_report, price_analysis, hot_opportunities). The style is readable and snake_case is consistent, but there is no single predictable pattern across the set.
Eight tools is a well-scoped size for a government tenders intelligence server. Each tool covers a meaningful workflow area without redundancy or bloat.
The tool surface covers the full read-only intelligence workflow: searching tenders, resolving entities, retrieving a tender's complete lifecycle, analyzing pricing, surfacing opportunities, and generating counterparty/unit/vendor reports. No obvious dead ends or major missing operations for the stated domain.