setSimDevice

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

With no annotations provided, the description carries the full burden and succeeds. It discloses persistence ('change persists on the session'), live propagation ('pushed live to a connected app without a reconnect'), event generation ('device_changed event lands in getEventLog'), and capability effects ('drives glasses.display.isAvailable'). It also explains the no-display degradation behavior, making the tool's side effects highly transparent.

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 dense and information-rich, with every sentence providing actionable detail. It is quite long and runs as a single unbroken block, and there is some repetition (e.g., display/no-display classification). It is appropriately sized for the tool's complexity but not maximally scannable.

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?

The description is highly complete: purpose, usage, behavior, persistence, eventing, and alternatives are all covered, which is impressive for a tool with no annotations or output schema. The omission of the brilliant models and the platform-switching refusal behavior (noted only in the schema) is a minor gap, and there is no mention of the return value, but overall the context is robust.

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 description adds meaningful context for the 'device' parameter (display panel differences, testing implications, identity surface), going beyond the schema. However, it omits two valid enum values (brilliant_halo, brilliant_frame) and incorrectly states only 'eight' simulatable models, creating an inconsistency with the schema. sessionId gets no explanatory value, but it is a standard identifier.

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 clearly states the action ('Switch the simulated glasses DEVICE MODEL') and the resource ('simulated glasses'), making the tool's purpose immediately obvious. It also distinguishes the tool from siblings by explicitly saying DON'T USE for camera scene (setSimVideo) or voice (injectTranscript), which is strong differentiation. The minor miscount of 'eight' models versus the ten in the schema does not obscure the core purpose.

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?

The description gives explicit when-to-use guidance ('USE before driving a display flow', 'test BOTH branches of a capability-gated feature headless') and when-not-to-use ('DON'T USE for the camera scene or voice'), even naming alternative tools. This is the gold standard for usage direction.

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