browser_open

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

With no annotations, the description carries the burden and does add useful behavioral context: persistent local logins/profile and a 20 MB RAM ceiling. It does not disclose tab/session side effects, failure modes, or timeout behavior, so transparency is partial but not absent.

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 dense sentences with no filler. The primary action and the most decision-relevant constraints are front-loaded, and every word earns its place.

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?

The schema covers parameters and the description provides the key operational constraints, so basic invocation is supported. However, without annotations or an output schema, and without explicit sibling differentiation, the description leaves return behavior and tool-selection context incomplete.

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 is 3. The description adds no parameter-level detail, but the schema already fully documents url, timeout, and session_id.

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 clearly states the action ('Opens a URL') and the resource ('stealth agent browser'), and adds differentiating context about persistent local logins/profile and a RAM ceiling. It doesn't explicitly name a sibling tool to distinguish itself from, but the core purpose is unambiguous.

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 usage contexts: use when persistent logins/profile are needed or when targeting local dev servers. However, it gives no explicit when-not-to-use guidance and doesn't reference alternatives like browser_navigate, leaving the routing decision partially to inference.

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