Run flow

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

No annotations, so the description carries the burden, and it discloses key runtime semantics: aborts on the first failure or app error, and returns an observe snapshot at the stop point. It also notes that each report line names the input path used. It does not state whether steps already executed before the abort remain applied to the app state (no rollback semantics), which is the main missing behavioral fact for a mutating batch 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?

Three sentences, front-loaded with the purpose and the alternative, with no filler. The middle clause about fiber-tree dispatch and per-step path naming partly duplicates the via enum description already in the schema, which is minor redundancy but keeps it from a 5.

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?

With no output schema, the description does cover the return behavior (stop-point observe snapshot, per-step report lines), which is the right call. But for a tool whose required parameter is an array of untyped step objects, the agent is left without the step vocabulary at the payload level (what fields tap/type/swipe/wait_for/expect take), so it cannot reliably construct a multi-step flow from this description alone.

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?

The core required parameter, steps, has an unstructured item schema (additionalProperties: {}), and the description compensates with a list of step kinds and a short example, which is real added meaning. However, via and observe already have detailed enum descriptions in the schema, so the description mostly restates them rather than adding new semantics, and the payload shape of each step kind remains undefined.

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 a sequence of UI steps server-side in one call' — and enumerates the supported step kinds (tap/type/swipe/wait_for/expect/expect_not/eval). It explicitly contrasts itself with the sibling tools tap and observe, so an agent can pick it without opening the 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 clear selection rule: 'Prefer this over many separate tap/observe calls,' naming the alternatives directly. It also explains the via:'js' tradeoff as the reason to batch. It stops short of stating when NOT to use it (e.g. a single interactive tap you want to inspect step by step), so it is strong but not fully exhaustive.

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