playwright__browser_run_code_unsafe

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

Annotations already indicate destructiveHint=true and openWorldHint=true. The description adds critical context: it runs code in the server process (not browser), is RCE-equivalent, and uses the word 'Unsafe' prominently. This aligns with the annotations and provides deeper behavioral insight beyond what annotations convey.

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 only two sentences but packs essential information: the action, the resource, and a stark safety warning. No redundant words or filler.

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, combined with the schema and annotations, gives a solid understanding. However, it omits mention of prerequisites (e.g., an open page context) and does not specify what the function returns (though the example shows a return). For a high-risk tool, slightly more context on expected preconditions would be beneficial.

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?

Both parameters have clear descriptions. The 'code' parameter includes an executable example and explains how the function is invoked with a 'page' argument. The 'filename' parameter clarifies precedence when both are provided. Schema coverage is 100% with no ambiguity.

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' with a specific verb and resource. It immediately flags the tool as 'Unsafe: executes arbitrary JavaScript in the Playwright server process and is RCE-equivalent', which sharply distinguishes it from sibling tools like playwright__browser_evaluate that run JavaScript in the browser context.

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 implicitly warns against casual use by labeling it 'unsafe' and 'RCE-equivalent', but it does not explicitly state when to choose this tool over alternatives (e.g., playwright__browser_evaluate for browser-side code). No when-not-to-use or prerequisite conditions are given.

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