browser_extract

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

No annotations are provided, so the description carries full burden. It only states 'Read text content' without detailing non-destructive behavior, page load waiting, dynamic content handling, or if navigates the browser. More behavioral context is needed.

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?

Two sentences deliver key information efficiently. No fluff, front-loaded with action and variations.

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 simple read tool, the description covers basic functionality. Missing details like id parameter purpose, error behavior, page loading guarantees, and output structure. With no output schema or annotations, more completeness would help.

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 selector parameter's behavior is explained ('returns innerText of matching elements'), adding value beyond the schema. However, the required id parameter lacks description in both schema and description, leaving its purpose unclear (likely tab/window ID). 50% coverage is partially compensated.

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 reads text content, with or without a CSS selector, and specifies the output (innerText). This distinguishes it from siblings like browser_snapshot (screenshot) and browser_eval (JavaScript execution).

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 when to use the tool (extracting text), but lacks explicit guidance on when to include a selector vs. not, and does not compare to alternatives like browser_eval for text extraction. No when-not or alternative tool mentions.

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