等待人工完成登录/验证

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

Annotation Contradiction: the description says mode=confirm 'clears pending state', which is a state mutation, while annotations declare readOnlyHint=true. The description is otherwise behaviorally rich (polling, timeout bounds, return values), but the direct contradiction with readOnlyHint makes the annotation untrustworthy for an agent.

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 front-loaded with the trigger case, then organizes modes in a consistent, scannable structure. Every sentence covers a distinct aspect—trigger, mode behavior, and return values—with no filler.

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?

With no output schema, the description correctly covers return values (screenshot, current URL/title) and explains all three modes plus timeout defaults and limits. The main gap is that it does not state the result or error shape when wait times out, nor explicitly mention a prerequisite connection, though cdpPort and sibling context partially cover that.

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 description coverage is 100%, so the baseline is 3, but the description adds meaningful semantics for mode behavior and timeout semantics (e.g., detect returns immediately and can be polled, wait polls until completion, timeoutMs only applies to wait). note and cdpPort are not expanded beyond the schema, but the schema covers them.

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 trigger (login expiry, captchas, WeChat scan) and a specific action: pause the automation flow and wait for human intervention. The three modes are individually described, making the tool's role unmistakable and clearly distinct from siblings like take_screenshot.

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 explicitly says when to use the tool (when login/verification needs human handling) and gives mode-level guidance, including the note that detect suits clients with tool timeout limits and can be repeatedly polled. However, it does not name alternative sibling tools or state explicit when-not-to-use conditions.

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