Switch assist/auto

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

Without annotations, the description carries the behavioral burden. It explains that 'assist' pauses for director review at each phase gate and 'auto' runs to completion without stopping. It mentions a prerequisite ('route locked') for using 'auto'. However, it does not describe side effects, permission requirements, or what happens to existing state, which is a minor gap.

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?

The description is two sentences long, front-loaded with the action ('Switch conversation mode'), and efficiently defines both mode options and use cases. No wasted words.

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 state-changing tool with two parameters and no output schema or annotations, the description covers the core functionality and use cases. However, it lacks explanation of the 'tid' parameter, return behavior, and potential errors, leaving some gaps for an agent to infer.

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 coverage is 0%, so description must explain parameters. It explains the 'mode' parameter well (meanings of assist and auto). However, it does not mention the 'tid' parameter (task ID) at all. The description adds value for half the parameters but leaves the other half undocumented.

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 clearly states the tool's purpose: switching conversation mode between 'assist' and 'auto'. It uses a specific verb-resource combination ('切会话模式' meaning switch mode) and distinguishes from sibling tools by focusing on mode control, not reading or running logs.

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?

The description gives concrete usage guidance: switch to 'auto' after route is locked for unattended completion, and switch back to 'assist' if stuck. It explains default behavior ('assist' for cost). However, it does not explicitly mention when not to use or contrast with alternatives like agent_start or agent_stop.

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