run_steps

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), the description discloses a key behavioral trait: 'Stops at the first failure,' which tells the agent about partial execution semantics. It also explains that then/then_chars appends the resulting page after the run, which is useful context on side effects. It doesn't state that successful earlier steps remain applied after a mid-run failure.

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?

Purpose is front-loaded in the first clause, followed by a compact step grammar with zero filler. The terse DSL notation is efficient but slightly cryptic on first read; still, every token carries information.

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?

An output schema exists, so return values needn't be described. Given the tool's complexity (arbitrary action batching), the description covers step grammar, target resolution, failure behavior, and the optional page-append option. What's missing is the shape of failure reporting and confirmation that prior steps persist after stopping.

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?

With 0% schema description coverage, the description must carry the full burden, and it does: it enumerates every step action type with its fields (click/hover {target}, type {target,text,submit?}, fill {fields,submit?}, press, select, scroll, wait, goto, back), defines 'target' as a snapshot ref or selector, lists legal then values, and explains then_chars. The density is high but a few details (scroll amount units, wait ms semantics) are left implicit.

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+resource ('Run several page actions in one call') and immediately names the value proposition (saves round trips). This cleanly separates it from the many single-action siblings (click, hover, type_text, fill_form), so an agent can tell instantly that this is the batching entry point.

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 parenthetical 'saves round trips' makes the intended context clear: use when you have multiple sequential page actions to perform rather than calling the single-action siblings repeatedly. It does not explicitly state when NOT to use it (e.g., when you need to inspect page state between steps), so it falls short of the explicit when/when-not/alternatives bar.

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