execute_adb_shell

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

The description correctly says it executes a command and returns output, implying a read/execute behavior. However, it does not disclose that raw ADB shell commands can have side effects, that the command runs with shell privileges, or that certain commands may hang or return empty output. With no annotations provided, the description carries the full burden but only partially covers behavioral risk.

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 sentences, front-loaded with the main verb and resource, and the parameter explanation is placed near the end. It is appropriately sized with no filler, though the second sentence is somewhat redundant with the schema, which costs it a point.

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 raw execution tool with no output schema and no annotations, the description is thin. The agent is not told what the output looks like (e.g., stdout/stderr, exit code, formatting), how to handle errors, or what environments this applies to (e.g., only when an Android device is connected). A tool with this much power and ambiguity needs more context to be safely invoked by an agent.

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?

With schema description coverage at 0% and only one required parameter, the description must add meaning beyond the bare schema field name. It says the `command` parameter is 'the shell command to execute,' which adds a minimal explanatory layer but lacks detail such as expected format, quoting requirements, or whether adb shell prefix must be included. It does not compensate enough for the zero schema coverage.

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 and resource: 'Executes a raw ADB shell command on the connected Android device and returns the output.' This clearly differentiates it from sibling tools like input_tap, get_battery_level, or install_apk, which target specific device functions rather than arbitrary commands. It doesn't name a sibling explicitly, but the 'raw ADB shell command' framing makes its niche obvious.

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?

There is no explicit guidance on when to use this tool versus alternatives. The description does not mention which sibling tools handle specialized operations (e.g., input_keyevent or install_apk) or advise preferring them over raw commands. Its general-purpose nature is implied, but nothing tells the agent when raw shell is appropriate or inappropriate.

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