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

Annotations already cover the safe-read profile, but the description adds substantial behavioral context beyond them: the filtering rule (only free + your devices), the presence of a `host` field for remote-host devices, the shared udid convention, and the Apple TV touchscreen limitation with the exact tool workarounds. This is exactly the extra operational detail an agent needs and could not derive from annotations.

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 core purpose and filtering rule are front-loaded in the first sentence, and the device-class specifics follow in a logical order. It is dense and long, but nearly every clause is substantive (field names, tool routing, key codes) rather than filler, so it earns most of its length.

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 discovery tool with no output schema, the description helpfully names the fields an agent will see (host, os, deviceClass, osLabel) and explains the two TV device classes that behave differently. Return shape and ordering/pagination are not spelled out, but nothing critical to correct invocation is missing.

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. The description still adds value by explaining that every device tool accepts a device's udid the same way and that host-scoped devices carry a `host` field, priming the agent for how returned identifiers feed sibling tools.

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 specific verb and resource ('List available devices (Android and iOS) across every connected device host') and defines scope precisely (only free devices plus devices currently used by you). It does not explicitly name a sibling like device_info to differentiate itself, which keeps it just short of a 5, but an agent can still tell what this tool does without opening the 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?

Gives concrete usage context: which devices appear in the list, and explicitly which downstream tools apply to edge cases. Notably it routes the agent away from ios_tap/ios_swipe/ios_send_keys on Apple TV and toward tvos_select/tvos_focus/ios_tv_button instead. It stops short of naming alternative list/discovery tools, so no full when-not-vs-sibling statement.

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