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

With no annotations, the description carries the full disclosure burden and does so well: it reveals that the tool steps the focus ring until it holds focus, presses Select by default, and can reach elements not on screen. It does not cover failure behavior when the label is not found or whether focus changes are reversible, which keeps it short of a 5. No contradiction with 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?

Three dense sentences: scope, mechanism, and cross-tool routing, with no repeated schema text. The most important operational constraint, 'Apple TV only,' is front-loaded, and every clause contributes behavior or routing information. This is appropriately sized, not bloated.

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 tool with no annotations and no output schema, this description gives strong operational context: what it focuses, how it locates elements, how to source labels, and which siblings handle related actions. It is missing explicit failure/timeout behavior and a direct comparison to tvos_select, but overall an agent can invoke it correctly from this text.

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; the schema already describes all three parameters. The description adds practical guidance — read ios_page_source for the label, home-screen tiles carry the app in their label, and select:false only moves focus — but this supplements rather than replaces the schema. The extra guidance is useful, but does not raise the score above the baseline.

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 first sentence names a concrete action and resource: move focus to an element matching a label or accessibility identifier on Apple TV, optionally pressing Select. 'The TV equivalent of tapping by label' and 'no coordinates' clearly distinguish it from coordinate-based tap tools, and it explicitly notes it can reach off-screen elements. This is far from a tautology and separates it from generic tvos_select.

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 states the clear context (Apple TV only), instructs the agent to read ios_page_source for the label, and routes remote-key actions to ios_tv_button and text entry to ios_tv_text. What it does not do is explicitly say when to prefer tvos_focus over the sibling tvos_select, or when select:false is the right choice, leaving some selection inference to the agent.

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