start_run

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

Annotations already declare destructiveHint=true, idempotentHint=true, readOnlyHint=false and openWorldHint=true, so the safety profile is covered. The description usefully adds the 'no embedded source code' scoping rule and the mandatory model/idempotency key, but says nothing about the danger-full-access path, the approval token, or what destruction actually entails.

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?

Three compact sentences, the core action front-loaded and constraints following. No filler, though it could be organized slightly more clearly around the parameter groups.

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?

For a destructive, open-world tool with 10 parameters, nested objects and no output schema, the description covers the required fields and a key constraint but omits the escalation/permission machinery (danger-full-access, approval token, dangerous-permission confirmation) an agent needs to call it safely.

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?

With only 40% schema description coverage, the description must compensate and does partially: it explains that workspace/targetLocations/task carry scope and that model and idempotencyKey are mandatory. But permission, timeoutMs, codexAllowedTools, workspaceApprovalToken and confirmedDangerousPermission get no coverage in either place.

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?

The description states a specific verb and resource – '启动持久 Cursor Agent 运行' (start a persistent Cursor Agent run) – so the agent knows exactly what the tool does. However, it does not explicitly distinguish this from siblings such as open_run or wait_run, leaving the agent to infer the boundary.

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?

It gives prerequisites (must explicitly select model and idempotency key) and a constraint (read-only/workspace-write only accept workspace, target locations, task scope), which implies usage context. But there is no explicit when-to-use / when-not-to-use guidance versus the many sibling run tools.

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