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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=false, so the safety profile is carried structurally. The description's one genuinely additive behavioral fact is that launch answers with its first screen. It does not disclose per-action consequences (e.g., that uninstall discards app data or terminate kills a running process), nor prerequisites such as needing a prior upload for install.

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?

Nothing is filler — every clause maps to a real action — but the whole definition is a single semicolon-chained run-on that is hard to scan and mixes app lifecycle, permissions, and device settings with no grouping. It is compact yet poorly structured for an agent parsing 16 actions.

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 an 8-parameter, no-output-schema, multi-action tool with full schema coverage and existing annotations, the description covers what each action does but omits prerequisites (install needing the phone_upload_link flow, default device/session resolution) and the natural follow-up tools for inspecting the screen after launch. Adequate but with visible gaps for a tool this broad.

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%, so every parameter is already documented in the schema, including per-action value formats and the request_key retry pattern. The description largely restates that mapping (URL, permission, lat,long, push, .storekit) rather than adding new meaning. Baseline 3 applies when the schema does the heavy lifting.

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 description names the resource (a cloud iPhone app) and enumerates the concrete operations it performs — launch/install/terminate/uninstall, permissions, location, push, storekit, and device settings. That enumeration lets an agent recognize the tool's scope without opening the schema. It never distinguishes itself from near-neighbors like phone_app_run, phone_ui_act, or phone_ui_look, so it stops short of a 5.

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?

There is no when-to-use guidance, no exclusions, and no named alternatives despite obvious overlap with phone_app_run, phone_ui_act, and phone_ui_look. The only contextual hint is the behavioral note that launch returns its first screen. An agent must infer the choice of this tool versus its siblings purely from the action names.

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