run_task

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

No annotations are provided, so the description carries full burden. It discloses that the tool returns immediately with a task ID, that results must be polled via get_task, and suggests using take_screenshot to verify. While it does not cover authorization or rate limits, it gives good behavioral context for handling the async nature.

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?

The description is well-structured: starts with core purpose, lists specific use cases, gives a clear exclusion, and provides usage tips. Every sentence adds value, and it's concise without being too brief.

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?

Given no output schema and 4 parameters fully described, the description covers return behavior (task ID), polling, and verification steps. It also references sibling tools appropriately. The context is complete for effective tool invocation.

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?

Input schema has 100% coverage, so baseline is 3. The description adds value by explaining that max_steps should be increased for complex multi-step tasks, and reinforces that instruction should describe the end goal. This extra context justifies a 4.

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 clearly states the tool performs UI automation on a device. It lists specific use cases like opening apps, tapping, swiping, typing, etc. It also explicitly distinguishes from sibling tool take_screenshot by stating 'Do NOT use this tool to only take a screenshot — use take_screenshot instead.'

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 description gives explicit guidance on when to use (e.g., 'Use this tool for: Opening apps and performing tasks') and when not to use (screenshot). It also instructs to provide only the end goal, not low-level steps, which helps the agent use the tool correctly.

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