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 of behavioral disclosure — and it fails completely. For an arbitrary code-execution tool, there is no disclosure of execution scope (page context vs. browser context), side effects, persistence, return value format, asynchronous behavior, or permission requirements. The agent cannot assess the impact of running a script.

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 only two words, which reads as severe under-specification rather than conciseness. There is no front-loaded qualifying detail or narrative, just a bare phrase. A real conciseness win would pack useful context into a short space; this simply omits everything.

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 dangerous, unannotated code-execution tool with no output schema, this description is wholly inadequate. An agent cannot determine what the script runs against, what it returns, how errors surface, or what side effects persist in the session. Given the tool's complexity and risk profile, this falls far short of a minimum viable definition.

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 description coverage is 100%, so the baseline is 3: the schema already documents both parameters ('JavaScript to execute' and 'Session name'). The description adds nothing beyond the schema, not even context tying the parameters together. It neither improves nor degrades the schema's own coverage.

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?

'Execute JavaScript' is nearly a tautology of the tool name 'browser_eval' — it states a verb and resource but is barely more informative than the name itself. It does not differentiate from sibling tools like browser_console or browser_react, which also deal with script/code execution contexts. An agent choosing among 39 browser tools gets no discriminating information here.

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?

There is zero guidance on when to use this tool versus browser_console, browser_react, browser_state, or any of the other 38 siblings. No conditions, no alternatives, no exclusions are mentioned. The description provides nothing to help an agent route to the correct tool.

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