adb_shell

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

With no annotations provided, the description carries the full burden of disclosing behavior. It states the tool requires confirmation and is non-interactive, implying potential destructiveness, but does not detail side effects, permissions, or return value characteristics.

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 brief with two short sentences, containing no extraneous words. It is front-loaded but could benefit from additional structure, such as separating usage notes.

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 has 4 parameters, no annotations, and an output schema (not described), the description is insufficient. It lacks information about outputs, how to get a confirmation token, and edge cases for a generic command executor.

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 description adds no information about the four parameters (serial, command, timeout, confirmation_token). Schema description coverage is 0%, and while parameter names are somewhat self-explanatory, the confirmation_token parameter is unclear and the description fails to explain how to obtain or use it.

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 that the tool runs an arbitrary non-interactive adb shell command. The verb 'Run' and resource 'adb shell command' are specific. However, it does not explicitly differentiate from sibling tools like adb_logcat or adb_install_apk, though the term 'arbitrary' implies generic use.

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 only mentions that the tool always requires confirmation, but provides no guidance on when to use this tool versus alternatives, such as specific adb commands for specialized tasks. There is no explicit context for when not to use it.

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