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

The annotations only declare it is a non-destructive write, while the description adds real behavioral detail: what each tile actually does (wifi/mobile_data off takes the network offline, dark_mode changes the colour scheme, dnd stops banners), the platform-specific tile sets, and a concrete failure mode (tile_not_visible when the panel is closed). That is meaningful context beyond the structured fields.

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 in the first sentence, followed by effects, the tile vocabulary, and the failure condition in a logical order with no filler. The platform tile lists are dense but each item is load-bearing given the absence of enums in the schema.

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 three-parameter mutation tool with no output schema, the definition covers purpose, valid tile names, observable effects, and one failure mode. It does not say how to verify the resulting state (e.g. via get_settings) or what happens when setting 'value' to a state the tile is already in, which are the remaining gaps.

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 67% and the description compensates heavily for the undocumented 'tile' parameter by enumerating the exact closed vocabulary for Android and iPhone, which the schema does not do (0 enums). The 'value' semantics (boolean or 0-100 for brightness, omit to flip) are already in the schema, so the description adds little there, keeping this just below the top score.

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 opening sentence gives a specific verb and resource ('Flip a quick-settings tile in the open shade or Control Center'), and the closing note about tile_not_visible scopes it to an already-open panel. That scope distinguishes it from siblings like open_control_center and set_device without needing to open either schema.

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?

Usage context is clear: the tool operates on tiles in an open panel, it is compared to set_device for what it changes, and the tile_not_visible failure implies the panel must be opened first. What's missing is an explicit routing statement (e.g. 'call open_control_center/open_notifications first, use set_setting for non-tile settings'), so it stops short of full when/when-not guidance.

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