create_research_job

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

由於沒有 annotations，描述必須自行承擔行為揭露。它清楚說明任務會持久化、回傳 job_id、且不會立即執行，這些都是讓智能體避免誤以為呼叫後就同步得到研究成果的關鍵行為。雖然未談權限或副作用，但對建立任務類工具已足较誠實。

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?

開頭一句話載明核心功能，隨後用精簡清單列出全部參數語意，沒有冗句或重複 schema 已有資訊。每個條目都有資訊價值，適合 LLM 快速掃讀。

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?

對一個 8 參數、無輸出 schema、無 annotations 的非同步建立工具而言，描述已覆蓋呼叫所需的主要語意與回傳值。但「sources 預設全部」未列舉實際可用來源，也未明確說後續可透過 run_research_job 執行已建立的 job，稍有缺漏。

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 參數描述覆蓋率為 0%，描述完全補償了這項缺口。它為每個參數賦予語意和範圍：breadth 1-6、depth 1-3、max_papers 50、format 的枚舉值、critique 的紅隊對抗含義、langauge zh/en，question 也定義為科學問題。這比 schema 本身資訊更豐富，智能體能據此正確填寫參數。

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?

描述開頭就明確說出核心動作「创建深度调研任务」，指出資源是研究任務，並補充關鍵行為：M10 持久化、返回 job_id、不立即執行。這能與 run_research_job、execute_research、deep_research 等立即執行類兄弟工具明確區分。

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?

「不立即執行」暗示此工具適合需要先建立任務、稍後再跑的場景，與執行型兄弟工具形成隱含對比。但描述沒有明確寫出「需要立即執行時請改用 run_research_job/execute_research」，也沒有列舉不適用情境，因此只到隱含使用指引的層級。

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