handoff

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

The description discloses the blocking/waiting behavior, the banner UI, and that the call returns on click or timeout, including redirects. It does not fully describe the Cancel path or side effects if the user navigates away, but the core interactive behavior is transparent.

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 compact and front-loads the main behavior while adding necessary usage guidance. It is slightly dense with punctuation and clauses, but every sentence contributes useful information.

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?

The description explains when to use the tool and what happens for pick_element, but it does not fully specify the return value for the normal handoff case. It says the call returns on click or timeout, but not what data or status the agent should expect, and Cancel behavior is ambiguous.

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 descriptions already cover all parameters, and the tool description adds helpful context for message, timeout, and pick_element. It does not add additional meaning for tab_id beyond the schema, but overall the parameters are well understood.

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 a specific action—handing the browser to the user—and scopes it to tasks only a person can perform, such as 2FA, CAPTCHA, login, or a choice. It also distinguishes the optional pick_element mode, making the tool's purpose unmistakable.

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 ('for what only a person can do') and includes a strong directive ('Never type credentials yourself') that guides an agent away from attempting those tasks with other tools. The pick_element sub-behavior is also clearly explained.

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