act

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

With no annotations, the description carries the full burden and delivers: steps are effect-checked, one snapshot returns at the end, the batch stops early on no-effect/failure/submit-pay-delete controls, selector 'skips ref safety checks', and allowSensitive defaults off and is audit-logged. These are exactly the mutation/safety facts an agent needs and cannot get from the schema.

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 default behavior and uses every clause to carry information; nothing is padding. The telegraphic, backtick-dense style packs a lot into a small space, which is efficient but makes the middle ('cond = {...}') harder to parse on first read.

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 12-action batch tool with no output schema and no annotations, the description covers the return behavior (one snapshot at the end), batch limits (20 steps, repeat cap 25), early-stop conditions, block nesting depth, and a safety default with audit implications. An agent can invoke this correctly without further context.

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 baseline is 3, but the description goes well beyond it: it spells out the shape of read ({ref|find|selector, attr?} or {contains}), the one-level block structure (repeat {steps,until,max}, if {cond,then,else}, assert {cond}), the cond union ({urlContains|selectorExists|textContains, not} OR-ed, or element state), and the ref-vs-find rule tied to re-render scope.

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 concrete verb+resource: batch browser steps in one call, with the snapshot returned at the end. It implicitly distinguishes itself from the single-action siblings (click, type, select, fill, key) by claiming to be the 'DEFAULT way to act' and by warning that batching saves a model turn. The name 'act' itself is vague, but the description resolves it well within the first clause.

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?

Explicit when-to-use ('batch every step you can predict', default on form wizards), when blocks apply (repeat for pagination/load-more, if for optional banners, assert for page-match), and a crisp ref/find routing rule: inside repeat use find/selector never ref, elsewhere ref until re-render then find. Alternatives and exclusions are named rather than left to inference.

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