run_browser_task

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

With no annotations provided, the description carries the full burden, and it does so thoroughly. It discloses that results are evidence rather than verdicts, that verified is always false, and that page_text_untrusted may contain adversarial text that must be treated as data, not instructions.

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 dense but highly structured, with usage modes, return semantics, and a security warning packed into a compact set of sentences. Every sentence adds actionable information and important caveats are front-loaded.

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?

Given no output schema and no annotations, the description still tells the agent how to invoke the tool, how to continue or redirect a session, what evidence fields to inspect, and how to handle untrusted page content. Nothing essential for correct use 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?

The schema has 0% description coverage, so the description must compensate. It clearly explains url, goal, and session_id by mapping them to start/continue/redirect modes, but it does not describe timeout_s, leaving that parameter to its self-evident name and default value.

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 names a specific action and resource: 'Drive a browser toward a goal,' with clear modes (start, continue, redirect) and a precise statement of what it returns. It also distinguishes itself from fetching public content with a fetch tool, which helps an agent understand the tool's niche.

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 explains when to pass url and goal, when to pass session_id alone, and when to redirect with session_id and goal. It also gives a clear when-not-to-use rule: not for fetching public content readable with a fetch tool.

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