browser_run_code_unsafe

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

With no annotations, the description carries the full burden. It explicitly discloses the tool is RCE-equivalent and executes code in the server process, which are critical behavioral traits. It does not mention additional traits like session impact or error behavior, but the RCE disclosure is a strong, central warning.

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 sentence that conveys the core action and a critical safety warning. Every word earns its place: no redundancy, front-loaded with purpose and risk.

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 dangerous code-execution tool, the description gives the essential risk warning and execution context, but it lacks guidance on appropriate use cases (e.g., fallback when other tools are insufficient) and potential side effects. The schema covers parameter details, but the description is minimal for such a powerful tool.

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 input schema already provides detailed descriptions for all three parameters, including the relationship between 'code' and 'filename'. The tool description adds no extra parameter-level semantics, so the baseline of 3 applies.

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 it runs a Playwright code snippet, identifying the action (run) and resource (code snippet). It further specifies it executes arbitrary JavaScript in the Playwright server process, which distinguishes it from sibling tools like browser_evaluate (likely page-context evaluation).

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 an advanced catch-all tool for running raw Playwright code, but it does not explicitly state when to use it versus alternatives. The warning 'Unsafe' is a cautionary note, not usage guidance; it lacks direct comparison to sibling tools like browser_evaluate.

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