find_element

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

The description discloses return metadata (confidence, selection reason, fallback alternates) and implies a search with timeout. However, it does not mention side effects, permissions needed, or whether it modifies state. Since no annotations exist, this is partial transparency.

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 well-structured sentences, front-loaded with action and resource. No fluff; every sentence adds value.

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?

Despite no output schema or annotations, the description covers input purpose and output structure. Could mention that it requires a device/app context, but given sibling tools, the domain is clear. Reasonably complete for a find operation.

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, but the description adds semantic context like 'by semantic query' and lists specific attribute types (text, content-desc, etc.) not in the schema. It also clarifies return type, enhancing parameter understanding.

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 finds a UI element by semantic query using attributes like text, content-desc, resource-id, class, and specifies that it returns best match with metadata. This distinguishes it from siblings like tap_element (tap) or get_ui_tree (tree dump).

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?

No guidance on when to use this tool versus alternatives such as wait_for_ui or expect_element_visible. Does not specify preconditions (e.g., screen loaded) or scenarios where it should be avoided.

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