browser_open

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

There are no annotations, so the description carries the full transparency burden. It does disclose an important behavior beyond launching: reattaching an existing managed session. However, it does not explain what 'managed' means in practice, how long sessions live, or what happens to a session when the tool returns.

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 a single compact sentence with no filler. It front-loads the primary action with launch and adds the important reattach behavior without expanding the description unnecessarily.

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?

For a low-complexity tool with a fully described schema, this is mostly adequate. The main gap is that with no output schema and no annotations, the description does not say what the caller receives after successfully launching or reattaching, nor how the session relates to the rest of the tool family.

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 the baseline applies. The description itself adds little parameter context, but the schema already explains url, mode, devTools, and the VNC limitation on headful mode, so this is acceptable.

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 uses specific verbs, 'Launch or reattach', and clearly identifies the resource: a managed headful/interactive browser session. This distinguishes it from the sibling task, schedule, and inspection tools by focusing on browser session lifecycle rather than task or schedule management.

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 implies this is for starting or resuming an interactive headful browser session, but it does not explicitly state when to use this tool versus alternatives. Since the sibling list includes inspector-related tooling, some guidance on when browser session creation is required would clarify selection.

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