Predict Next UI Action

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

Annotations already indicate the read-only, idempotent, and non-destructive nature. The description adds behavioral context by explaining the prediction is based on 'transition success rates and goal alignment,' which goes beyond the annotations and illustrates how the tool operates.

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 a single, front-loaded sentence that directly conveys the tool's function without any redundant or filler content.

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?

Given the simple parameter set, rich annotations, and clear schema, the description provides enough context to invoke correctly. It does not describe the return format, but the tool's name and purpose make that less critical, and no output schema exists to require it.

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 input schema has 100% coverage with descriptive comments for each parameter. The description reinforces the goal-related purpose but adds no additional parameter-level semantics beyond what the schema already provides.

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: predict the best next UI action based on the current visual state, transition success rates, and goal alignment. It distinguishes itself from sibling tools like analyze_screenshot (analysis) and get_navigation_paths (path enumeration).

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 provides clear context for use: when you have a current visual state and need to decide the next action, optionally guided by a goal. It does not explicitly list alternatives or when not to use it, but the context is sufficient.

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