Run Android Sequence

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that execution stops on errors, that input commands are batched into one shell invocation, and that wait_for_element only verifies accessibility UI presence rather than application success — a genuinely non-obvious trap. It does not say what a stopped run returns, whether already-executed steps persist, or what permissions/device state are required.

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 dense sentences, front-loaded with the core capability and followed by the two most consequential behavioral facts. No filler, no restatement of the tool name.

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 complex tool with a 100-item array of six step variants, no annotations, and no output schema, the description covers sequencing, batching, and error-stop semantics but says nothing about the result shape (which step failed, how far execution got). An agent can call it, but cannot reason confidently about failure recovery.

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 description adds no meaning for the `steps` or `device` parameters beyond what the schema already encodes; the device parameter already has its own schema description covering env fallback and auto-selection. The wait_for_element sentence does clarify how one step variant should be interpreted, which is modest added value, so it sits at the baseline for a partially covered schema.

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?

The description gives a clear verb and resource — 'Run ordered Android actions' — plus the distinguishing mechanism, 'batching consecutive input commands in one ADB shell'. That differentiates it from the single-action siblings like android_tap or android_swipe, though it never names an alternative explicitly.

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?

Usage is only implied: the phrase 'ordered actions' and the batching detail suggest this is for multi-step flows where per-call latency matters, but there is no explicit 'use this when X, use android_tap when Y'. The wait_for_element note is a correctness caveat rather than routing guidance.

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