Browser actions

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

The description adds substantial behavior beyond annotations: ordered execution, stop-on-first-error with action identification, partial effects remaining, no retries, auto-wait/scroll behavior for element targets, coordinate/wheel non-waiting behavior, button release on cancelled/timed-out clicks, and load-wait scope. These details are consistent with destructiveHint=true and give the agent a precise operational picture.

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 front-loaded with the core purpose and return behavior, then adds operational constraints in compact sentences. Every sentence carries useful information, with no repetition or filler.

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 complex, destructive, open-world tool, the description covers execution order, error behavior, partial effects, retry policy, waiting semantics, and return format. The schema supplies parameter details and session prerequisites, so the description is complete enough for an agent to invoke the tool correctly.

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%, so the schema already documents parameters thoroughly. The description still adds actionable semantics by clarifying that element mouse targets auto-wait and scroll into view while coordinate and wheel actions do not wait, and that load waits observe the current document rather than future navigation.

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 states a specific verb and resource: run ordered browser actions covering mouse, field, key, dialog, and wait categories. It also distinguishes the output profile by returning plain text without a snapshot, making the tool's role clear relative to screenshot/extract/fetch siblings.

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 usage through its list of interactive action types, but it does not explicitly say when to choose this tool over browser_evaluate, browser_extract, browser_fetch, or other siblings. There are no named alternatives or exclusions, so routing is left partly to inference.

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