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

Annotations only declare the safety profile (non-readonly, non-idempotent, non-destructive); the description adds the OCR fallback, the candidate-ranking heuristic favoring interactive widgets, the ~150ms EditText focus-settle wait, and the exact return timing. That is rich behavior beyond what annotations 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?

Purpose is front-loaded and every sentence carries operational content (fallback, ranking, timing, sequencing). It is dense and long, and 'Both tools are first-class' is slightly editorial, but nothing is wasted filler.

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-param tap tool with no output schema, the description covers matching strategy, fallbacks, return timing, and interaction with the sibling type tool. An agent has everything needed to invoke it correctly and sequence it safely.

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 baseline is 3, but the description adds real semantics: how text/contentDesc/resourceId interact, that resourceId pins a specific element, and why text is preferred. It doesn't cover maxScroll/autoScroll/scrollDirection beyond the schema, keeping it just short of a 5.

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 verb+resource ('Find a UI element ... and tap it') and immediately scopes the resource types (text, content-description, resource-id). It clearly differentiates itself from device_tap and device_type by name, so an agent can route without opening schemas.

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?

Explicitly names when NOT to use it (image-only icons, Canvas widgets, dynamic/localized labels) and the alternative (device_tap with bounds from device_page_source). It also states the critical sequencing rule relative to device_type (call before, do not parallelize) and the resourceId pinning escape hatch.

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