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

Annotations are sparse (readOnlyHint false, no destructive specifics), so the description carries heavy burden and delivers: it distinguishes focused-empty (text:"" focused:true) from failed-write (text:null focused:false), explains null is typically a display-attachment problem, and discloses that it won't wake the TV to avoid losing focus. This is exactly the behavioral context the annotations don't provide.

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?

Four tight sentences, each earning its place: purpose, the focused-field prerequisite, the null/empty distinction, and the no-wake rationale. Front-loaded with the core action.

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?

Covered thoroughly for a 3-param tool with no output schema. Return-shape ambiguity (text vs focused) is the main source of agent error and it's addressed explicitly; the no-wake behavior and display caveat complete the picture.

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 description coverage is 100% — the schema already documents op (get/set/append/clear), text, and udid. The description adds no parameter-level detail beyond what the schema provides. Baseline 3 per the coverage rule.

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 (read or write) on a specific resource (the focused text field / on-screen keyboard buffer on an Apple TV). It distinguishes itself from siblings by naming ios_tv_button as the navigation prerequisite, and from device_type/ios_send_keys which operate on iOS devices generally.

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?

Clearly states the precondition: a field must actually be focused, and directs the agent to ios_tv_button to get there. It also explains it deliberately doesn't wake the TV. It stops short of explicitly routing between get/set/append/clear alternatives, though the schema enum descriptions cover those.

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