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

Annotations already establish read-only/idempotent/non-destructive, so the description correctly spends its budget on subtler behaviour: the `features` block is the device's claim reported as-is, possibly wrong, and `power_state` describes the box, not display attachment. The explicit warning that a screenshot can fail on a TV reported as On is exactly the kind of non-obvious detail annotations cannot convey.

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 summary of what is reported, then ranks the two gotchas (untrustworthy `features`, `power_state` vs display). Every clause carries information; there is no boilerplate or repetition of the title.

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?

There is no output schema, so the description must name the returned fields — it does (paired, awake, foreground app, playing, features, power_state) and flags the failure modes of each. For a single-parameter read tool this is fully sufficient.

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?

With a single parameter and 100% schema description coverage ('Apple TV UDID or name'), the schema already carries the semantics, so a 3 baseline is appropriate. The description adds no further guidance on resolving the udid/name argument.

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?

Opens with a specific verb+resource ('Report an Apple TV') and enumerates exactly what is reported: pairing state, awake state, foreground app, and current playback. This cleanly separates it from the many neighbouring ios_tv_* tools (ios_tv_power, ios_tv_apps, ios_tv_button) that act on a TV rather than report on it.

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?

'Cheap, and the right first call — nothing else here works on an unpaired TV' tells the agent when to reach for this tool first and why it is a prerequisite for the sibling ios_tv_* calls. It stops short of naming a specific alternative to use instead, so the when-not side is only implied.

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