browser_eval

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

With no annotations, the description carries the full burden and does well: it discloses the SSRF guard that blocks internal addresses, that an empty url runs against the current page, that the JS must return a value via `return`, and that the output is page data rather than instructions. Permission/rate-limit and error behavior are still unstated, so not a 5.

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?

Short and front-loaded: purpose first, then a labeled 'КОГДА' block, then edge-case notes. Every sentence adds information; only the ExecuteScript reference is somewhat gratuitous if that tool is not a sibling.

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?

An output schema exists, so return values need no explanation. Given that, the description covers purpose, usage, the url default, SSRF constraints, and the return requirement, leaving it essentially complete for a 2-param eval 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?

Schema coverage is 0%, so the description must compensate for two undocumented params. It clarifies the empty-default behavior of `url` and the return contract for `js`, which is meaningful, but the `js` parameter's shape/context (what page scope it runs in, what globals are available) is left implicit.

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?

States a specific verb+resource: execute the agent's own JS on the page and return the result as JSON. The DOM-extraction/calculation framing makes it distinguishable from fetch_page and web_search. It does not explicitly name a sibling it is not, so it stops short of 5.

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 'КОГДА' block gives clear context for when to reach for this tool: pulling fields out of the DOM, computing, extracting data under custom rules. That is real usage guidance, but no explicit when-not or named alternative (e.g. 'use fetch_page for a plain GET') is given.

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