Batch Commands

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

Annotations already flag destructiveHint=true and openWorldHint=true, so the risk profile is known. The description adds a non-obvious behavioral rule: the device argument applies to every step unless a step overrides it. This is useful beyond the schema, which only describes device as a string. It does not contradict annotations, and the added context is meaningful for safe execution.

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, zero filler. The purpose is front-loaded, the example makes it concrete, and the device-inheritance rule is a single sentence at the end. Every word earns its place; it is compact yet complete for the main intent.

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 batch tool with no output schema, the description does not mention what the return value looks like (e.g., per-step results or error aggregation), nor does it address the stopOnError and listElementsAtEnd options beyond their schema descriptions. Since these options materially change behavior and the tool aggregates multiple actions, the description could be more complete. However, the schema and annotations carry much of the load, so it is adequate but not fully self-contained.

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 all parameters have basic descriptions. The description goes further by clarifying the inheritance behavior of the device parameter across steps, which is not in the schema. It also hints at the step structure ('same as calling it directly') reinforcing the schema's meaning. This adds genuine semantic value beyond the structured data.

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 states a specific verb ('Run multiple tools in sequence') and resource (a batch of mobile tools), and gives concrete examples ('click, type, click, type'). It clearly distinguishes from the sibling tools, which are individual mobile actions, by framing this as a sequence orchestrator. The purpose is unambiguous and immediately actionable.

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?

It explicitly recommends using this tool for multi-step flows ('Use this to fill forms or perform multi-step flows without round-trips'), which gives a clear when-to-use. It does not explicitly state when not to use it (e.g., for single actions use the individual tools), but the implied context is sufficient for an agent to route correctly. The device-inheritance rule also adds operational guidance.

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