oc_browser_control

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

The description discloses important behaviors such as no automatic visible-browser restart, the need for an operator-controlled restart in headless mode, and that pause/resume are tied to tracked handlers. It does not fully describe side effects of verify or status beyond checking conditions, but annotations provide no additional hints.

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 compact but dense, packing several important operational nuances into a few sentences. It avoids redundancy and front-loads the core purpose.

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 description gives enough operational context to use the tool, but it does not describe the output format or what exactly status/verify return, especially the lease object required for resume. Given no output schema, this would have been helpful.

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 already covers all parameters, and the description enriches key ones: it explains that expectedUrl is compared including query and fragment but not echoed, and that resume requires the lease returned by pause. This adds meaningful semantic detail beyond the schema.

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 tool's purpose: observe a managed tab, check caller-supplied conditions, or pause automatic input for human control. It covers the main actions (status/verify/pause/resume) and distinguishes it from pure observation or interaction tools.

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 practical guidance about waiting for phase=human, draining tracked tool handlers, and the requirement to resume with the returned lease and expected URL. However, it does not explicitly state when to prefer this tool over sibling tools like oc_observe or interact.

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