apps_host_input

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

Annotations already declare destructive=true, openWorld=true and non-idempotent, and the description adds genuinely new behavioral facts: the gating check against ai_capabilities, the prohibition on caller-supplied script/selectors, and a post-call verification step. It stops short of saying what state may be destroyed or how failures surface, which keeps it off a 5.

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?

Front-loads the gating condition and prerequisite before the mechanics, and nearly every sentence carries a distinct constraint. The phrasing is dense to the point of being terse, but there is no 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 destructive, open-world UI automation tool with four required parameters, nested event object and no output schema, the definition covers gating, coordinate frames, input modalities, exclusions and verification. The remaining gap is the meaning and provenance of instanceId/generation and what a call actually returns, which is only hinted at.

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 only 25%, so the description must carry weight; it does clarify the most error-prone semantics (normalized 0..1 coordinates over the whole host window, scroll in CSS pixels, allowed key set). However instanceId and generation are never explained, only indirectly pointed at via 'Read apps_input_targets first,' leaving two of four required params semantically thin.

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-and-resource pair ('Open and operate Menu or Device for the active device App') with a clear scope qualifier. It implicitly separates itself from the App-viewport sibling by stressing coordinates are relative to the 'ENTIRE host window ... not the App viewport,' though it never names apps_interface_input outright, so the distinction requires inference.

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?

Gives hard preconditions ('only when ai_capabilities.hostMenus enables that surface and AI owns control'), an explicit prerequisite ('Read apps_input_targets first'), and negative scope ('Does not operate permission/AI approval, access-management or lifecycle controls'). An agent knows both when to call it and when to skip it.

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