ui_interact

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

No annotations are provided, so the description carries the full burden. It discloses locator resolution priority, x/y fallback behavior, validation behavior with analysis_id, iframe context selection, expect_input verification, and default post-click observation of portals/messages/dropdowns/notifications. This is unusually transparent.

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 dense but every sentence contributes: purpose is front-loaded, then resolution order, fallback semantics, validation, frame logic, and observation behavior. A bulleted or grouped structure would improve scannability, but the length is justified for a 20-parameter tool with no schema descriptions.

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 high complexity (20 params, no annotations, 0% schema coverage), the description covers behavior and many parameters well. However, it leaves critical gaps around valid action values and the meaning of value/key/in_iframe/settle_ms/timeout_ms. The output schema reduces the need to describe return values, but the missing action semantics prevents full self-sufficiency.

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?

With 0% schema description coverage, the description compensates substantially by explaining css, role, name, description, xpath, text, placeholder, x/y, analysis_id, frame, expect_input, and max_results. However, the required action parameter's accepted values are not described, and value/key/in_iframe/settle_ms/timeout_ms are only implied or omitted.

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?

States a specific action ('executes unified DOM interactions') and target ('current page/active iframe'), and describes the returned focused overlay result. However, it does not explicitly contrast itself with siblings like ui_click or vtable_cell_click, so sibling differentiation is left implicit.

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?

Provides clear operational conditions: CSS is preferred when the analyzer returns it, x/y are only fallbacks, analysis_id triggers pre-execution validation, frame defaults to the active AntD tab iframe, and expect_input verifies focus. It lacks explicit 'when not to use this tool' or named sibling alternatives, but the within-tool usage context is strong.

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