browse_act_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 so well: stop-on-failure semantics, the authorization requirement for sensitive actions, the meaning of observe='summary' vs 'snapshot', and retry guidance. Minor gap on rate limits or what a 'navigation receipt' contains.

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?

Front-loaded with the core action and stop condition, then the step catalogue, then return values and observe modes. The step-type enumeration is dense but every entry earns its place since the schema is empty. Slight redundancy in restating stop conditions twice.

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?

No output schema exists, and the description compensates by describing the return payload (completed steps, remaining count, extract rows, failure/navigation receipt). For a batch executor with two loosely-typed parameters this is nearly complete; only per-field defaults and an explicit batch-size limit are missing.

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 0% and 'steps' is an opaque array of arbitrary objects, so the description has to define the shape itself — which it does by enumerating each step type with its accepted keys (selector/text/nth, value/press_enter, amount, fields, maxRows, url). observe is also given meaning. Not exhaustive on per-field types or defaults, but far more than the schema offers.

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 one short batch of page actions', with the batch scope ('short', 'stop on failure or navigation') made explicit. This clearly separates it from the single-action siblings (browse_click, browse_fill, browse_press), though it never names them.

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 operational context: stops on failure or navigation, requires explicit user authorization for sensitive/destructive actions, and warns not to repeat a step whose receipt reports failure. It does not explicitly say when to batch versus when to issue individual browse_* calls, so an agent must infer that.

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