web_eval

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

With no annotations provided, the description bears the full burden of disclosing behavior. It mentions running arbitrary JavaScript, implying potential destructive actions or side effects, but provides no safety warnings, no details on session impact, and no explanation of return value format beyond 'last expression's value'. This is insufficient for safe execution.

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, very concise. However, it omits essential details (e.g., how to provide the JavaScript code), making it under-specified. While no words are wasted, the lack of completeness reduces its effectiveness.

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 tool is conceptually simple but the description fails to cover critical aspects: no input schema for the required JS code, no output schema, and no explanation of return value structure. This leaves the agent unable to correctly invoke the tool without additional information.

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 has zero properties, yet the description says the tool runs arbitrary JavaScript. This implies a critical missing parameter (the JavaScript code), contradicting the schema. The description adds no meaning to the empty schema and actively misleads by suggesting an input that isn't defined.

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 arbitrary JavaScript and returns the last expression's value, providing a specific verb and resource. However, it fails to differentiate from similar sibling tools like chrome_evaluate_js and safari_evaluate_js, which also evaluate JavaScript in browser sessions.

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 offers no guidance on when to use this tool versus alternatives (e.g., browser-specific evaluate JS tools). There is no mention of prerequisites, context, or exclusions, leaving the agent without decision support.

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