browser_run_code_unsafe

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

The description adds substantial behavioral detail beyond the destructiveHint annotation by specifying that it executes arbitrary JavaScript in the Playwright server process and is RCE-equivalent. This discloses the security-critical execution environment and potential for full server compromise, which is crucial for an agent deciding whether to invoke it.

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 two sentences: the first states the tool's purpose, the second delivers the critical safety warning. Every word earns its place, with no fluff or redundancy.

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 high-complexity, dangerous tool with no output schema, the description covers the most essential context: the RCE risk and server-process execution. It does not explicitly state return-value behavior, but the schema's example (return await page.title()) implies the result is returned. This is adequate given the schema's richness and the warning's clarity.

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% with detailed explanations for both parameters: code includes a full example showing the function signature and usage of page, and filename explains precedence when both are provided. The tool description adds no additional parameter semantics, so baseline 3 is appropriate.

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 'Run a Playwright code snippet' and immediately highlights the unsafe RCE-equivalent nature, distinguishing it from browser tools like browser_evaluate that run in page context. The verb 'run' and resource 'Playwright code snippet' are specific, and the warning makes the tool's unique position unmistakable.

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?

No explicit alternatives or when-not-to-use conditions are given. The unsafe/RCE warning implies caution and suggests this is an advanced/risky tool, but there is no direct guidance such as 'prefer browser_evaluate for in-page JavaScript' or 'use only when other browser tools are insufficient.' Usage context is implicit, not explicit.

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