browser_start_human_control

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

With no annotations, the description carries the full burden and does it well: it discloses the side effect of raising the window, the blocking behavior (every command on that tab fails except browser_take_snapshot), and the underlying constraint that agent-driven physical input never reaches the page. These are exactly the traits an agent could not infer from the schema.

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?

Five short sentences, front-loaded with the action, then the reason, then the consequences and the exit. Every sentence carries information the agent needs; 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?

Zero required parameters, no output schema, no annotations — the description covers purpose, side effects, blocked-command behavior, and how to detect completion and resume. Nothing an agent needs to invoke it correctly is missing.

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 tabId, windowId, and showWindow are already documented. The description only echoes the window-on-screen behavior tied to showWindow and adds nothing about tab/window targeting, so baseline 3 applies.

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?

States a specific verb and resource: hand the tab to a person for real keyboard/mouse input. It is clearly distinct from browser_stop_human_control and browser_take_snapshot, both of which are named in context.

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?

Gives explicit triggers ('a password, a code sent to them, a captcha, proving who they are') and the reason the agent cannot substitute for them. It also names the exit path (browser_stop_human_control) and the only command that keeps working, so the when/when-not picture is complete.

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