docs(ui-automation): prefer label/id targets for tap guidance #214
+35
−12
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Tighten ui-automation tap guidance so agents target accessibility selectors first and only fall back to coordinates.
Today, agents often tap by guessed coordinates when they do not have a fresh accessibility snapshot, which is brittle and causes flaky automation. This updates the tap tool schema messaging, validation copy, and published tool/skill docs so the default guidance is: use
id/labelfirst, coordinates second.I considered only changing skill docs, but that leaves tool metadata and validation errors still nudging coordinate usage. Updating schema + manifest + generated docs keeps guidance consistent across MCP clients and CLI users.
Additional context: docs were regenerated via
npm run docs:updatesodocs/TOOLS.mdanddocs/TOOLS-CLI.mdreflect the updated tool description.