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

Annotations already declare mutation, non-idempotency, and non-destructive behavior. The description adds useful context beyond annotations: steps run in order, changes are reported, no-op taps are reported, first failure stops the rest, and multilingual text is round-tripped. It still does not describe the response shape or session-level constraints.

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 description is front-loaded with purpose, then gives a compact grammar and behavioral notes. The dense pipe-separated step list is appropriate for a complex action language and every sentence carries operational information.

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 complex UI-action tool, the description covers purpose, step syntax, sequencing, failure behavior, and no-op reporting, while annotations cover safety and the schema documents auxiliary parameters. It could more explicitly connect to phone_ui_look as the observe-first sibling and describe the return payload, but it is largely complete.

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, but the description substantially expands the critical steps parameter by enumerating supported step forms and optional arguments. Device, session_id, and request_key semantics are left to the schema descriptions, so it is not a complete 5.

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 states a specific action (do steps on the Simulator) against a specific resource (a cloud iPhone screen), and the step grammar makes the tool's scope concrete. It does not explicitly differentiate itself from phone_ui_look or phone_app_control in the main description, though the steps schema references phone_ui_look.

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?

The description gives a clear context for use: executing ordered UI steps and returning what changed, with failure stopping the sequence. However, it never explicitly says when to use this instead of phone_ui_look or phone_app_control, nor does it state prerequisites, so usage is implied rather than routed.

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