Shell

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

No annotations are provided, so the description carries the full burden. 'Raw' suggests unparsed, unrestricted command execution with destructive potential, but the description does not warn about side effects, permissions, device selection, or what state the command runs against — significant omission for an arbitrary-command executor.

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?

A single short, front-loaded sentence with zero filler. Its brevity is stylistically clean, though here it borders on under-specification rather than economy.

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?

An output schema exists so return values need not be described, but for a raw arbitrary-command tool with no annotations and no parameter documentation, the description is far too thin — an agent gets no safety, scoping, or device-targeting context.

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 and does not. The word 'adb shell' loosely contextualizes `cmd` as a shell command string, but the `device` parameter (which device the command targets when null-defaulted) is entirely unexplained in both schema and description.

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?

States the mechanism ('raw adb shell') and frames it as an 'escape hatch', which distinguishes it in spirit from the structured interaction tools (tap, swipe, type_text). However, it never says what resource or device it operates on, and the differentiation from siblings is implied rather than stated.

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 phrase 'escape hatch' hints this is a fallback for cases the structured tools don't cover, but there is no explicit when-to-use or when-not-to-use guidance, and no sibling is named as the preferred alternative for common operations.

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