adb_shell_open

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

With no annotations, the description carries the burden of behavioral disclosure. It mentions returning the initial banner output and describes auto-discovery behavior (errors if 0 or >1 devices) and connection details (no probing, log directory follows alias). Still, it does not disclose session lifecycle (e.g., session remains open until adb_shell_close) or prerequisites like ADB connectivity.

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 main description is two succinct sentences that front-load the core purpose. The parameter details are structured within the schema and are relevant and well-organized. No filler or redundant text.

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 simplicity and no output schema, the description adequately covers the main functionality and return value (banner output). It could be more complete by referencing the companion close tool or session lifecycle, but the sibling list and 'interactive session' terminology provide enough context for an experienced 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?

The parameter description far exceeds the schema, explaining when to pass an alias vs serial, how serials are resolved back to aliases, the exact behavior when omitted (auto-discovery with error conditions), and a note about log directories. This adds substantial semantic value beyond the schema's simple 'Target device alias'.

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 action ('Open an interactive ADB shell session') and the resource ('Android device'). It distinguishes itself from siblings like adb_shell_exec (which executes one-off commands) and other shell open tools by specifying 'ADB shell' and 'interactive session'.

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 parameter description gives practical guidance on device selection (prefer alias, omit only for single device) and explicitly notes there is no need to call adb_device_list. However, it does not provide explicit when-to-use vs alternatives, such as contrasting with adb_shell_exec for single commands or explaining when to use adb_shell_open instead of other session types.

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