Browser Handoff

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

With no annotations provided, the description carries the full behavioral burden. It correctly discloses the core behavior (foregrounding the browser, delegating to a human) and the follow-up step. However, it does not disclose what happens during the handoff — whether the tool blocks until the human finishes, whether there is a timeout, or how the session is affected — which matters for an agent deciding how to sequence actions.

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?

Two sentences totaling roughly 25 words, with the core action and purpose front-loaded and the follow-up instruction placed second. Every word earns its place; there is no filler or redundancy.

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?

An output schema exists, so return values need not be explained in the description. The description covers the core invocation scenario and sequence adequately, but it omits parameter semantics and any statement about waiting/timeout behavior. For a tool of this simplicity, this is a minimum-viable description with a few meaningful gaps.

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 0% and the description mentions none of the three parameters (device, message, session). Since coverage is below 50%, the description was expected to compensate but does not. The parameter names are conventional and self-hinting, but an agent gets no guidance on what 'message' is for (e.g., a prompt shown to the user) or how 'session' scopes the handoff.

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 verb and resource ('bring the browser to the foreground') with a concrete purpose (human finishes a login or captcha). It also differentiates itself from siblings by naming its continuation flow ('call browser_read afterwards'), making clear this is the human-handoff tool rather than a programmatic browser action or an input-injection tool.

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 clear context for when to use the tool: when a human must complete a login or captcha by hand. It provides a sequencing guideline (follow with browser_read), but it does not explicitly state exclusions such as 'use browser_act when no human interaction is needed' or contrast with sibling tools like type_text or tap.

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