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

Goes well beyond the annotations (readOnly=false, idempotent=true, destructive=false): it discloses that orientation lock can make the call a no-op, that the device auto-rotates independently, and that the response reports the ACTUAL re-read orientation (including FACE_UP/FACE_DOWN when flat), which may differ from the request. This is exactly the kind of behavioral context annotations can't carry.

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?

Front-loaded with the core action, then the caveats, and every sentence carries information. The session requirement sits at the end after the behavioral nuances, which would be more discoverable earlier, but overall it is tight and waste-free.

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 2-param mutation with no output schema, the description covers prerequisites, the default-resolution ambiguity, failure modes (lock/auto-rotate), and the shape of the returned value, so an agent has everything needed to call and interpret it correctly.

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%, so parameters are already documented; the description still adds genuine meaning by explaining that LANDSCAPE resolves to whichever rotation the session lands on (default LANDSCAPE_LEFT) and when to prefer the explicit directional values. Marginal but real value over the enum.

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 states a specific verb+resource ('Set the screen orientation of an iOS device') and covers scope well. It does not differentiate from the near-neighbor siblings ios_rotate / device_orientation / device_rotate, so an agent cannot tell from the text alone why it should pick ios_orientation over ios_rotate.

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?

It gives clear usage context: use the generic LANDSCAPE when direction doesn't matter, ask for LANDSCAPE_LEFT/RIGHT when it does, and notes an active iOS automation session is required as a prerequisite. No explicit when-not or named-alternative routing, which keeps it below a 5.

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