Native OpenClaw browser control

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

The annotations already declare destructive/open-world behavior and the description adds capability context such as tab lifecycle, files, and batch actions. No contradiction exists, but concrete side effects (e.g., closing tabs, downloading files, dismissing dialogs) are not spelled out.

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 short and readable, with the key prerequisite and constraint front-loaded. It avoids boilerplate, though the phrase 'Full high-level' is slightly redundant.

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?

With 65 parameters, nested objects, and no output schema, the description provides only broad categories and leaves the agent without enough information to construct valid calls or interpret results. No return value or error behavior is mentioned.

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 0% and the description does not explain any of the 65 parameters, their relationships, or required combinations. Even the referenced 'opaque handle' is not explicitly mapped to the handle parameter.

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 identifies this as the high-level OpenClaw browser control surface for tabs and lists the supported capability categories (tab lifecycle, DOM interaction, evaluation, etc.). It also differentiates it from raw shell/target ID access, though it doesn't name sibling tools explicitly.

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 instructs the agent to call list_shared_tabs first and pass the opaque handle, and warns that raw shell/target IDs are not accepted. However, it does not explain when to prefer this tool over the sibling actions like navigate, click, or type.

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