get_ui_elements

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that the result is a numbered text list with no image and that the call is cheaper, but it does not cover prerequisites such as device connection state, whether element numbers are stable, or how they map to tap_element.

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?

Two short sentences deliver the purpose, return format, and cost comparison with no wasted wording. The key distinction from screenshot is front-loaded.

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 zero-parameter inspection tool, the description is mostly complete: it explains what is returned and why it is cheaper than a screenshot. It could add how the numbered elements relate to tap_element, but the core invocation context is sufficient.

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 takes zero parameters, so the baseline is 4 and no parameter semantics are needed in the description. The schema and description are consistent.

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 gives a specific verb and resource: "Get the numbered list of on-screen elements." It further specifies the element types (text, buttons, inputs) and distinguishes the tool from the sibling screenshot tool by saying it returns no image and is cheaper.

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?

"Cheaper than screenshot" clearly signals when this tool is preferable to taking a screenshot. However, it does not explicitly mention alternatives such as tap_element or state exclusions, so it falls short of full when/when-not guidance.

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