browser_eval

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

No annotations are provided, so the description carries the full burden. It states that JS runs on the page and hints at side effects like scrolling, but does not disclose the return value, error behavior, asynchronous handling, or the potential for arbitrary side effects on the page. This is thin for a powerful eval tool.

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?

One concise, front-loaded sentence that states the core action first and then lists useful application examples. Every word serves a purpose and no redundant detail is present.

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 has no annotations, no output schema, and only a minimally described parameter, so the description must carry substantial contextual load. It names the operation but omits critical operational details like return format, page context caveats, error propagation, and side-effect warnings, leaving an agent to ricognize how to safely and correctly use the tool.

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 schema provides only a required string parameter 'js' with no description. The description implies js is the JavaScript code to execute, but does not explain whether it should be an expression, statement, async function, or how the result is returned. With 0% schema coverage, the description should compensate more strongly.

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 uses a specific verb ('Evaluate'), names the resource ('JS on the page'), and gives concrete examples that distinguish it from sibling browser interaction tools. It clearly conveys what the tool does and why an agent would choose it.

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 examples—extract hidden JSON, scroll, dismiss cookie banners—provide concrete scenarios where evaluating JS is appropriate. It does not explicitly state exclusions or name alternative tools, but the context is clear enough for typical browser automation decisions.

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