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

Annotations only supply the generic safety profile (readOnly=false, idempotent=false, destructive=false, openWorld=false); the description adds the non-obvious behavior that matters: focus is invisible so blind presses can land anywhere, the top shelf contains purchase flows, and menu/home differ in navigation-stack semantics on tvOS 27. That is exactly the kind of side-effect disclosure annotations cannot express, and nothing here contradicts them.

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-loaded with purpose, then the button list, then the two high-value surprises; every sentence carries information an agent needs. The all-caps 'TWO THINGS THAT SURPRISE CALLERS' framing and the slightly essayistic final clause cost it a point, 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?

With 4 parameters at full schema coverage and no output schema, the description need not document returns, and it does cover the surprising side effects, the wake-to-home behavior, and a safe-press workflow. It omits failure modes (unreachable/asleep TV with wake=false, pairing requirements implied by ios_tv_pair_begin) and any hint of what a call reports back.

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 the baseline is 3, but the description earns an extra point by attaching semantics to specific enum values: it explains that action turns a press into a double tap or hold, and that the `menu` value pops a navigation stack while `home` exits the app. These are behavioral meanings of the parameter values, not restatements of the enum list.

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 concrete verb+resource ('Press a button on an Apple TV remote') and enumerates the full button surface (d-pad, select, menu, home, playback/volume), so the agent knows exactly what scope this covers. It does not, however, resolve overlap with siblings like ios_tv_volume (whose keys also appear here as volume_up/volume_down) or tvos_select, so the boundary against alternatives is left implicit.

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 real operational guidance: 'take a screenshot before pressing select' because focus is unreported, and explains that menu does not exit a programmatically launched app while home does — a concrete when-to-use-which rule. It stops short of naming sibling alternatives (ios_tv_swipe, tvos_select, ios_tv_volume) or stating prerequisites such as a paired/sessioned device.

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