Execute shell command on device

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

With no annotations provided, the description carries the full burden and effectively discloses key behavioral traits: it warns of high risk ('extreme caution'), describes the action's scope ('can perform any operation on the device'), and specifies the return values ('stdout, stderr, and exit code'). It lacks details on permissions or rate limits, but covers essential safety and output information.

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 front-loaded with a warning, followed by clear statements on capability and returns, all in three concise sentences with zero wasted words. Each sentence adds critical information (risk, scope, output), making it efficiently structured and appropriately sized for the tool's complexity.

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 the tool's high complexity (arbitrary execution), no annotations, and no output schema, the description is largely complete: it covers purpose, risk, and return values. However, it lacks details on error handling or specific prerequisites (e.g., device connectivity), leaving minor gaps in context for safe usage.

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 description coverage is 0%, so the description must compensate, but it does not explain the parameters 'serial' or 'command' beyond what the schema's property names imply. The description adds no meaning to the parameters, such as clarifying 'serial' refers to device identifier or 'command' format, leaving them undocumented. Baseline 3 is given as it partially compensates by implying command execution context.

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 explicitly states the verb 'executes' and the resource 'shell command on device', clearly distinguishing it from sibling tools like android.file.pull or android.input.tap by focusing on arbitrary command execution via adb shell. It specifies the action and target without redundancy.

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 provides explicit guidance with 'Use with extreme caution', indicating high-risk scenarios, and implicitly suggests alternatives by noting it 'can perform any operation', implying more specific tools (e.g., android.file.push for file operations) should be preferred when available. It clearly defines when to use (arbitrary commands) and warns against misuse.

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