browser_act

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

With no annotations, the description carries the behavioral disclosure burden. It reveals the implementation approach ('rule-based DOM heuristics — no LLM dependency'), which is useful, but omits caveats about failure modes, side effects of actions, or whether actions are irreversible. This leaves the agent with incomplete safety awareness.

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 reasonably sized but contains promotional fluff ('GROUNDBREAKING', 'One tool call does what normally takes 5-10') that does not add operational value. The examples are useful but could be trimmed. Front-loaded enough, but not every sentence earns its place.

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 a single parameter, no output schema, and no annotations. The description explains the interaction model and lists varied examples, giving a general sense of capability. However, it does not mention return values, error handling, or limitations (e.g., unsupported page states), which is needed for reliable use in complex browser automation contexts.

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 100% with one instruction parameter, so baseline is 3. The description adds value through concrete examples of acceptable instructions, clarifying the natural language format and range of intents beyond the schema's minimal description.

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?

Clearly states it performs natural language page interaction, a distinct capability from sibling tools like browser_click, browser_fill, and browser_goto. The examples ('search for laptops under $1000', 'click the login button', 'fill email') concretely illustrate the scope.

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?

Implies use as a higher-level alternative to multiple discrete tool calls ('One tool call does what normally takes 5-10'). Provides examples across navigation, clicking, filling, extraction, and scrolling, which signal when it applies, but does not explicitly say when to prefer sibling tools like browser_eval or browser_waitForSelector.

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