browser_ask_user

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

With no annotations, the description carries the full burden and does so thoroughly: it enumerates every return status (acknowledged, action with all terminal values, values for done), explains the navigation/origin rules that terminate a prompt, the timeout default, the tab-activation and window-restore side effects, the immediate failure on error pages/about:blank, and the keystroke-visibility caveat. This is unusually rich behavioral disclosure.

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?

Front-loaded with the core purpose, and nearly every clause carries distinct behavioral information that an agent needs. The weakness is structural: it is one dense paragraph with heavy parentheticals instead of being grouped into purpose, inputs, returns, and caveats, which hurts scannability.

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?

There is no output schema, yet the description still documents the return contract in detail, along with failure conditions, security constraints, and tab/window side effects. Nothing an agent needs in order to invoke this 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 coverage is 100%, so the baseline is 3, but the description adds real meaning for the fields parameter by explaining its behavioral consequence (card vs. dialog) and its limited value visibility to the page. It also frames the action return values against the field input. It does not add much beyond the schema for title or timeout, keeping it below 5.

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: "Ask the user to do something or give information," and then pins down the two concrete modes (card without fields, dialog with fields). An agent immediately knows this is an agent-initiated prompt to the human. It never names a sibling (e.g. browser_handle_dialog or browser_solve_captcha), so the differentiation is implicit rather than explicit.

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 clear context for when to use it and how the two modes differ (simple Done/Skip confirmation vs. field collection), plus a prerequisite ("the tab must show a page that loaded") and a security condition (only ask for secrets belonging to the page the tab is on). There are no explicit exclusions or named alternative tools, so it stops short of a 5.

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