run_agent_task

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

The description discloses that the agent autonomously plans and executes multiple steps using screen vision and touch controls, which is important behavioral information (the agent has agency and may perform actions beyond a simple explicit one). The annotations already declare destructiveHint=true and readOnlyHint=false, which the description aligns with. It adds context that the agent is autonomous and may take multiple actions, which is valuable beyond the raw annotations.

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 a single focused sentence plus an example in the schema. It's front-loaded with the core purpose and adds the key behavioral detail about autonomous planning. Efficient and earns its space.

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 tool with 2 well-documented parameters, no output schema, and good annotations, the description covers the essential purpose, the autonomous execution mode, and the execution mechanism. It could mention what the return value looks like (task ID, result, etc.) since there's no output schema, but given the 100% schema coverage and sibling context, it's reasonably complete.

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 the schema already fully documents both parameters (goal and timeoutMs) with descriptions. The description adds some context by showing a concrete example ('Open WeChat and send hello to John') in the schema, and mentions timeouts indirectly. Baseline of 3 is appropriate since the schema carries the parameter documentation burden.

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 runs an AI agent task on the connected phone, explaining it plans and executes steps using screen vision and touch controls. It uses a specific verb+resource combination ('run agent task'), which distinguishes it from siblings like take_screenshot or get_device_status. However, it doesn't explicitly differentiate itself from related task tools like abort_task or get_latest_task.

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 conveys it's for multi-step goals achieved via vision and touch, implying usage for complex tasks. However, there's no explicit guidance on when to use this vs alternatives like take_screenshot or when not to use it. The distinction from simpler direct-action tools is implied but not spelled out.

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