browser_batch

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

With no annotations, the description carries the full burden and does real work: it discloses sequential execution order, fail-fast semantics ('stops at the first failure'), and that it returns a change set. It does not explicitly state whether already-executed steps are rolled back or persist after a failure, nor any permission requirements.

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?

Two compact sentences: the core behavior first, then an illustrative example and the failure rule. Every clause carries information; nothing is padding.

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?

There is no output schema, so 'returns the final change set' is the only clue about return values and it is not unpacked. Combined with no annotations, the description leaves the post-failure state of a partially executed batch underspecified for a mutating 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 100% and the schema itself explains that each item has the same fields as browser_act, so the baseline is 3. The description adds only a small increment, the {action:"wait", ms} step form and the ordering guarantee, without detailing other step fields.

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 and resource: run several browser_act steps in order in one call. Naming browser_act directly and framing it as a multi-step wrapper makes the distinction from the single-step sibling obvious without opening either schema.

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?

Gives a concrete usage scenario ('fill a whole form and click Save') that makes the intended case clear, and 'in one call' implies the efficiency motivation. It does not explicitly say when to prefer browser_act over batching, so there are no stated exclusions.

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