adb_shell

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

With no annotations to indicate safety, the description carries the full burden of behavioral disclosure. It merely says 'Execute a shell command,' which implies arbitrary and potentially destructive actions but does not warn about side effects, permissions, or the need for caution. This is a significant transparency gap for a tool that can modify system state in unpredictable ways.

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, efficient sentence with no redundant wording. It gets straight to the point and is front-loaded with the key action. However, it is so terse that it borders on under-specification, though not enough to be penalized heavily.

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?

This tool can execute arbitrary shell commands, making it potentially powerful and risky. The description provides no information about output format (stdout/stderr), exit codes, or risk considerations. With no output schema and no annotations, the description is inadequate for an agent to fully understand the tool's behavior and implications.

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?

The schema provides descriptions for both parameters ('Shell command to execute' and 'Target device ID (optional if only one device)'), covering 100% of the parameters. The description adds no additional meaning beyond what the schema already offers, so it meets the baseline for high 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 clearly states the tool's function: executing a shell command on an Android device. It uses a specific verb and resource, distinguishing it from sibling tools like adb_tap or adb_install_app. However, it lacks any detail about scope or limitations (e.g., arbitrary commands vs. specific allowed ones), so it's not as rich as a top-tier purpose statement.

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?

No guidance is provided on when to use adb_shell versus the many specific sibling tools (e.g., adb_force_stop, adb_clear_data). There's no mention of alternatives or scenarios where this generic shell tool is preferred. The description simply states the action without context, leaving the agent to infer usage.

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