ui_smart_fill

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

Annotations provide readOnlyHint=false and openWorldHint=true, signaling this mutates device state and operates on live UI rather than a closed world. The description adds the composite behavior (locating, tapping, typing, optional ENTER) and the label-to-nearest-field intelligence, which is value beyond annotations. However, it doesn't disclose edge behaviors like what happens with multiple matches, focus requirements, or failure modes.

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 sentences, fully front-loaded with the action sequence and the distinguishing smart-label behavior. No wasted words; every clause earns its place.

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?

With a 100% covered schema and an output schema present, the description doesn't need to explain return values. The composite find+type behavior is well captured, but given it's a complex multi-step tool with 9 params and a smart disambiguation step, a bit more on match failure or multi-step expectations would strengthen completeness.

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 all 9 parameters are documented. The description adds meaning by clarifying the two-part nature: search-based element location (text, contentDesc, resourceId, className, exactMatch, index) feeding into a type action (textToType, pressEnter). This helps an agent understand how search and action parameters relate, adding value beyond the individual field 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?

Description clearly states verb+resource (find, tap, inject text, press ENTER) with a distinguishing smart feature (finds nearest input field when targeting a label). It differentiates reasonably from siblings like tap, input_text, and form_fill, though it doesn't explicitly name them.

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 implies a composite action (find+tap+type) and mentions the smart label-to-field behavior, which gives some context on when it would be preferred. However, it does not explicitly state when to use this vs. alternatives like input_text, tap, or form_fill, nor any exclusions or prerequisites.

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