Evaluate Page JavaScript

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

Description adds specifics beyond annotations: 'arbitrary JavaScript can read or modify DOM, storage, page-visible credentials, and remote application state.' Aligns with destructiveHint=true and openWorldHint=true. No contradiction.

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?

Four sentences, each adding value: use case, preconditions, next steps, sensitivity. No redundant information. Well-structured and front-loaded.

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?

Covers when, preconditions, and risks. Does not explicitly describe output format, but output schema exists. Complete enough for an agent to understand the tool's role and safety considerations.

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 coverage 0%, so description must compensate. It clarifies the need for acknowledgeRawCapture and acknowledgeDangerousEval, but does not detail other parameters like maxBytes, frameName, timeoutMs. Partial but inadequate compensation.

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?

Description explicitly states when to use: when safe DOM, action, wait, or trace tools are insufficient and exact JavaScript execution is essential. Clearly distinguishes from sibling tools by focusing on arbitrary 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?

Provides detailed guidance: preconditions (active page, acknowledgeRawCapture and acknowledgeDangerousEval), next steps (prefer targeted tool afterward, document necessity), and sensitivity warning. Excellent context for when and how to use.

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