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

With no annotations, the description carries the full behavior burden and does so thoroughly: it discloses that AUTO-ROTATE is permanently turned off, explains why the accelerometer would otherwise override the setting, and describes the blocking behavior of waiting for the stream to report the new frame size. This lets the agent predict side effects and coordinate subsequent taps.

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?

Four tightly packed sentences: purpose, value semantics, side effect with rationale, and return/coordination behavior. Every sentence adds operational value, and the most important side effect is given prominent placement.

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 a two-parameter tool with no output schema and no annotations, the description covers the essential operational context: side effect, persistence, reverse-orientation semantics, and when control returns. Nothing an agent needs to invoke it correctly is missing.

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% and the schema already documents udid and orientation, so the baseline is 3. The description adds meaningful semantics to the orientation parameter by explaining the relationship to ios_orientation and the meaning of the reverse variants, so it earns a 4.

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 opening sentence gives a specific verb and resource: 'Set the screen orientation of an Android device.' It also distinguishes orientation values from ios_orientation and names the reverse variants, which helps separate this tool from the iOS sibling in the tool list.

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 orients the agent by mapping PORTRAIT/LANDSCAPE to ios_orientation and noting that reverse variants have no iOS counterpart, implying cross-platform routing. It does not explicitly state when not to use the tool or name other alternatives such as device_rotate, so it falls just short of fully explicit usage guidance.

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