read_orientation

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

With no annotations provided, the description carries the full behavioral burden. It indicates a read operation and notes that it returns the current device orientation, but it does not disclose potential sensor dependencies, error behavior, or whether this is safe/non-mutating beyond the word 'Read'.

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 description is short and front-loaded, immediately stating the tool's purpose. The 'Returns' line is slightly redundant with the first sentence but adds clarity about the output, and there is no filler.

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 simple no-parameter tool, the description is mostly sufficient, but the presence of closely related siblings such as read_quaternion and read_euler_angles creates ambiguity. The description does not clarify whether 'orientation' means high-level screen/device orientation or more detailed sensor orientation data.

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 tool has zero parameters and the schema description coverage is 100%, so there are no parameter semantics for the description to clarify. The baseline for zero-parameter tools is 4, and the description correctly adds no irrelevant parameter guidance.

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 the tool's function with a specific verb and resource: 'Read device orientation (portrait, landscape, etc.)'. However, it does not differentiate this from sibling tools like read_quaternion, read_euler_angles, or read_heading, which also relate to orientation data.

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 use this tool instead of alternatives. The sibling list includes read_all_sensors, read_quaternion, and read_euler_angles, but the description does not state which tool is appropriate for a given use case, leaving the agent to infer.

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