browser_run

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

With no annotations provided, the description carries the full burden of disclosing behavior. It reveals the tool may type values, but it does not disclose that the tool will likely navigate, click, wait, or perform multiple autonomous steps, nor does it mention side effects, failure modes, or the meaning of max_steps. This is a significant transparency gap for an autonomous browser-agent 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?

The two sentences are short and front-loaded with the core purpose, and there is no fluff. However, the description is so terse that it omits important operational details, so its brevity is not fully 'appropriate' for a tool of this complexity.

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 is an autonomous, multi-step browser runner with no annotations and no output schema, so the description needs to explain behavior, bounds, and success/failure signals. It only mentions pursuing a goal and supplying typed values, leaving max_steps, return behavior, navigation effects, and error cases entirely unaddressed.

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 0%, so the description must compensate. It gives weak semantic hints for 'goal' and 'values' ('Supply values for anything that must be typed'), but it does not clarify the expected format of the goal, how values map to fields/inputs, or what max_steps controls. The description adds only minimal meaning beyond the raw parameter names and types.

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 clear goal-directed action ('Pursue a whole goal on the current page') and 'whole goal' signals this is a higher-level operation than sibling primitive actions like browser_click or browser_type. It does not fully define what 'pursue' entails, but it distinguishes the tool from the surrounding action-level 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 instruction to 'Supply values for anything that must be typed' gives some practical guidance, and the phrase 'whole goal' implies this is for multi-step tasks rather than single actions. However, it never explicitly says when to prefer browser_run over browser_act or the other siblings, nor does it mention exclusions such as navigation limits or page-load expectations.

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