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

Annotations carry the safety profile (destructiveHint=true, idempotentHint=false, readOnlyHint=false), so the description could focus on added context. It instead adds only 'return output' and omits what makes this risky: arbitrary command execution, possible permanent device changes, permission/root requirements, and timeout or truncation behavior for long-running commands.

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 efficient sentence with the action front-loaded and no filler. It is appropriately sized, though the brevity is part of why behavioral gaps remain.

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 an arbitrary-code-execution tool flagged destructive with no output schema, the description should warn about irreversibility, required privileges, and result format. None of that is present, so an agent cannot predict consequences before invoking it.

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 coverage is 100% with both parameters ('udid', 'command') fully described, so the schema carries the load. The description adds nothing about command syntax, quoting, multi-command chaining, or output formatting beyond what the schema already states.

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 a specific verb (Execute) and resource (shell command) scoped to an Android device, and notes that output is returned. It is distinguishable from device_tap/device_key-style siblings, though it does not name a nearby alternative the way the best definitions do.

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 guidance on when to reach for a raw shell command versus a purpose-built device_* tool, no prerequisites (rooted device? adb access? timeouts?), and no mention of when-not-to-use. The agent must infer all of this.

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