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

No annotations are provided, so the description carries the full behavioral transparency burden. The description does disclose the behavior well - it explains it returns a ranked priority list, notes the coordinate mode picks the smallest containing element, and clarifies the return matches the UI inspector format. However, it doesn't disclose edge cases like what happens when multiple locators match, error behavior for invalid coordinates, or whether non-Android platforms are supported.

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 compact and front-loaded with the core purpose. The three sentences each earn their place: purpose+input modes, output format, and usage rationale. It doesn't waste words, though it could potentially be more concise by merging the last two sentences. Generally well-structured for a tool with 6 parameters.

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 tool with 6 parameters, 1 required, no output schema, and no annotations, the description covers the essential semantics well. It explains the dual input modes, the output format, and ties to page-object generation workflow. However, it lacks details on edge cases, failure behavior, or whether requesting both coordinates AND text simultaneously is an error. Given the tool's moderate complexity, this is a complete-but-not-exhaustive description.

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 schema has 100% coverage with descriptions for all 6 parameters (x, y, text, udid, resourceId, contentDesc). The description adds meaning beyond the schema by clarifying the mutual exclusivity of lookup modes ('Either coordinates OR text/contentDesc/resourceId'), noting x/y must be used together, and explaining that text matches both text AND content-desc (which the schema only hints at). This adds semantic value beyond the parameter descriptions.

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 clearly states the tool's purpose: generate ranked locator strategies for a UI element on Android. It specifies both supported lookup modes (coordinates OR text/contentDesc/resourceId) and explicitly describes the output (priority-ordered list matching the UI inspector format: id, text, content-desc, accessibility selector, XPath). This is a specific verb+resource combination that clearly distinguishes from siblings like device_find_element and device_elements_in_region.

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 gives clear input modes ('Pass either coordinates OR a text/contentDesc/resourceId') and states the purpose ('Use these to fill page-object selectors when generating test scripts'). It does not explicitly name alternative tools to use instead (like device_find_element for direct lookup), but the guidance that this replaces re-deriving locators is clear context. Missing explicit when-not-to-use guidance.

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