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

Annotations already declare non-read-only, idempotent, non-destructive, and the description layers on genuinely useful behavior: persistence across apps, SpringBoard relaunch with a 5-10s flicker, and delayed read-back of the value. These are side effects annotations cannot express.

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 compact sentences, front-loaded with the core effect and persistence warning, then the timing caveat, then the code-format constraint, ending with the alternative tool. 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 no output schema needed for a setter, all three parameters documented, and the disruptive/async side effects disclosed, an agent has everything required to invoke this correctly and to set expectations about timing.

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 literal field meanings are already documented. The description still adds non-obvious semantics: language must be a base code ("fr", not "fr-CA") because iOS refuses region-qualified languages and auto-splits a regional code into base language plus locale.

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?

"Change the iOS device's system language and / or locale" gives a specific verb (change) plus the exact resource and scope (persistent, affects every app). It is clearly distinguishable from per-app launch variants and from locale-clearing siblings like device_clear_app_locale.

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?

Explicitly routes the agent: "For per-app testing without changing the whole device, prefer ios_launch_app_in_language." That names the alternative and the condition that selects it, which is the strongest form of usage guidance.

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