browser_run_code

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

No annotations are provided, so the description carries the full burden. It adds the permission requirement, which is useful, but it does not disclose execution context, potential page modifications, return value behavior, or error handling—significant gaps for a code execution tool.

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?

A single, front-loaded sentence with no wasted words. It conveys the core action and primary constraint efficiently.

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 tool executing arbitrary JavaScript, this description is inadequate. It lacks information about success/failure indicators, what happens to the page, how the code is executed, and any safety caveats. With no annotations or output schema, the description needed to do more.

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 describes pageId and sessionId (67% coverage), and the description adds no parameter detail. The required 'code' parameter is left undocumented in both schema and description, so the description provides no extra meaning beyond the schema baseline.

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 runs page JavaScript, with a specific verb and resource. However, it does not distinguish itself from the sibling tool browser_evaluate, which likely performs a similar function, so it misses the full 5.

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 mentions a prerequisite (runCode permission) but provides no guidance on when to use this tool versus alternatives like browser_evaluate, nor any context about appropriate use cases. There is no when/when-not guidance.

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