添加 / 移除稍后再看

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

注解已声明 readOnlyHint=false、destructiveHint=true、idempotentHint=true，安全画像清楚；描述在此之上补充了注解无法表达的鉴权与开关要求（bili_jct Cookie、BILIBILI_ALLOW_WRITE 环境变量），这是真正增量信息。未说明失败场景（未登录/视频不存在）或移除操作是否可撤销，故非满分。

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?

两句话零冗余：第一句说明做什么，第二句前置警示鉴权与开关要求。信息密度高且前后顺序合理，安全警示紧跟用途之后。

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?

两参数、无输出 schema、注解已覆盖安全与幂等画像，描述的职责主要是说明用途与写入准入，这两点都做到了。剩余缺口是失败/错误行为与返回值形态未提及，但因无 output schema 且工具简单，属可接受范围。

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 覆盖率仅 50%：input 有描述（多种视频标识格式），action 仅靠枚举值自解释。描述中「加入或移出」恰好为 add/remove 提供了语义映射，但未补充 action 之外的行为差异（如 add 幂等、remove 后列表顺序等）。基线 3 合适。

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?

「把视频加入或移出「稍后再看」」以具体动词（加入/移出）指向明确资源（稍后再看列表），并直接对应 action 枚举的 add/remove。同名参数 input 接受 BV/av/ep/ss/短链，由 schema 补全，不与任何兄弟工具重叠，agent 无需打开 schema 即可区分。

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?

描述给出了可写前置条件（Cookie 含 bili_jct、BILIBILI_ALLOW_WRITE=true），这属于环境前提而非使用时机建议。没有任何「何时该用/何时不该用」或与 bili_video_info、bili_download 等兄弟工具的选择指引，agent 只能靠自己推断。

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