apple_system_capabilities

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds one genuinely new behavioral fact beyond annotations – that Automation permission is not exercised – which prevents a common misuse, but it says nothing about permission requirements for the call itself or response shape.

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?

Two short, dense sentences with the safety posture front-loaded in the first word. Every clause carries information; nothing is 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?

With no output schema, the description must convey what comes back, and it does by enumerating the four discovery categories. It stops short of describing the response structure or how 'allowed Shortcuts' is scoped, which is the only remaining gap for a zero-parameter probe.

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?

The tool takes zero parameters, so the baseline is 4 per the rubric. Schema coverage is vacuously 100% and there is nothing for the description to compensate for.

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 names a concrete verb ('discover') and enumerates the specific resources it surfaces: installed Apple apps, platform, file roots, and allowed Shortcuts. This is clearly distinguishable from every sibling (all of which act on a specific app or data type), though it doesn't explicitly name a sibling it replaces.

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?

It establishes usage context by exclusion: 'Read-only' and, critically, 'Does not test Automation permission' tell the agent this is an environment-inspection call, not a permission probe. There is no explicit 'call this before X' statement, but the scope boundaries are clear enough to route correctly.

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