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

No annotations are provided, so the description carries the full transparency burden and delivers comprehensively. It discloses the ~150ms focus-settle wait for EditText matches, the candidate-ranking heuristic (interactive widgets beat passive labels), auto-scroll behavior, and the critical parallel-call race condition warning about device_type. This far exceeds what structured fields would convey.

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 substantive but dense, packing multiple important behavioral caveats into what could be split more cleanly. The critical sequential-ordering warning is front-loaded after the focus-settle note, which is appropriately prominent. Every sentence carries information, though the length (approaching 700 characters) makes it a heavier read than strictly necessary; the CRITICAL note is slightly buried midway rather than leading.

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?

For a 7-parameter tap tool with no output schema, the description is remarkably complete: it covers selection strategy, fallback path, disambiguation rules, timing behavior, and concurrency constraints. Given the tool's complexity (scanning logic, ranking, auto-scroll, focus handling), this description provides everything an agent needs to invoke it correctly.

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 7 parameters are already documented in the input schema. The description adds value by explaining the semantic relationship between text/contentDesc parameters (both match via the 'text' param which 'matches text or content-desc'), clarifies the resourceId pinning behavior for multi-match disambiguation, and explains autoScroll/maxScroll intent. Minor deduction: scrollDirection semantics are clear from schema alone and don't need description reinforcement.

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 states a specific verb+resource ('Find a UI element by text, content-description, or resource-id and tap it') and clearly distinguishes this from the sibling device_tap(x,y) tool. It explicitly names the alternative (device_tap with bounds from device_page_source) and explains when each should be used, providing strong differentiation.

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 explicit when-to-use guidance ('NOT always usable — for elements without stable text/contentDesc/resourceId... use device_tap instead'), names the exact alternative tool, describes candidate ranking behavior, and gives a CRITICAL sequential-ordering instruction relative to device_type. This is exemplary usage guidance exceeding the rubric's 'explicit when/when-not/alternatives' bar.

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