browser_session

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

无任何 annotations，描述承担全部行为披露责任，但仅说明了会话隔离和持久化能力，未披露各 action（list/create/select/save/close）的副作用——尤其 close 可能销毁会话、save 可能写盘、select 会切换当前活动上下文。这些行为在 schema 的 enum 中可见但无说明。

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?

单句中文描述，核心动词在前，能力细节随后，没有任何冗余词。长度与工具复杂度基本匹配，但考虑到 5 个 action 的多模式工具，信息密度仍有提升空间。

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?

这是一个包含 5 个 action、4 个参数、无 annotations 的会话生命周期管理工具，复杂度较高。描述未覆盖各 action 的具体行为、会话生命周期（select 切换后旧会话是否保留、close 是否销毁保存的状态）等关键决策信息。有输出 schema 可豁免返回值说明，但其余上下文缺口明显。

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 参数描述覆盖率为 0%，描述必须补偿但只间接映射了 storage_state_path（通过"storage state 持久化"），对 name、session_id 的用途和 storage_state_path 是输入还是输出路径均未解释。action 枚举本身在 schema 中具有自解释性，但其余三个参数缺乏语义。

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?

描述使用了明确的动词"管理"和资源"隔离 BrowserContext 会话"，并补充了"账号 Cookie 环境切换"和"storage state 持久化"两个独特能力，能与 browser_start/browser_connect 等兄弟工具区分开。但未显式点名与浏览器连接类工具的分工边界，故不给满分。

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?

没有说明何时使用本工具而不是 browser_start、browser_connect、browser_close 等兄弟工具，也没有提及前置条件（如是否需要已启动的浏览器实例）或排除场景。使用场景只能从"会话管理"的语义中隐式推断。

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