skill_run

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

由于没有任何 annotations，描述承担了行为透明度的主要责任。它明确披露了权限沙箱、requiresApproval 返回、两段式 HITL 以及 approveAsks: true 授权后重试的机制，这些是关键的运行时行为。但它没有具体说明成功时的输出结构、错误码、超时行为或副作用，所以未到满分。

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?

一句话完成了“产在哪里执行 + 权限异常路径提示”两部分信息，没有冗余。信息前置，后续补充授权重试条件，结构紧凑，每个短语都有实际价值。

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?

该工具没有 annotations 或 output_schema，描述必须承担完整的路由和调用指引责任。虽然核心用途和 HITL 流程是清晰的，但成功/失败返回格式、inputs 对象的约定、timeoutMs 语义、grantTokenId 的用途都没有覆盖，agent 在真实调用时仍面临多个空白。

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?

输入 schema 有 6 个参数，而 schema_description_coverage 为 0%；描述只解释了 approveAsks 的含义，帮助 agent 理解 HITL 重试，但 task、inputs、timeoutMs、grantTokenId 等其余参数均未获得说明。由于 schema 本身没有字段注释，描述必须登记大部分参数语义，当前明显不足。

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?

描述用明确的动词“执行”和资源“单个 skill”概括了工具用途，并用“权限沙箱”限定了执行环境。这与 skill_search、skill_inspect 等检视类兄弟工具形成清晰区分。

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?

描述强调了“单个 skill”的语义，从而暗示与 workflow_run 等多 skill 编排工具的差别，但没有显式说明何时应该用这个工具、何时不应使用。缺少对兄弟工具的明确排他指引。

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