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

Annotations already declare this as a non-read-only, non-destructive, non-open-world action, but the description adds genuinely new operational facts: the call is a conditional no-op when no keyboard is shown, and a session is required with auto-start fallback. That auto-start/session detail is exactly the kind of behavior annotations cannot express. It does not describe what happens if no keyboard is present beyond the conditional framing.

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?

Two sentences, zero filler, with the action and its condition front-loaded before the session prerequisite. Every clause carries information the agent needs.

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 one-parameter, no-output-schema tool with annotations covering the safety profile, the description supplies the two missing pieces — the visibility condition and the session requirement. Return behavior is unspecified, but with no output schema that is a minor gap for a fire-and-forget UI action.

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?

There is a single parameter (udid) and the schema already documents it at 100% coverage, so the baseline is 3. The description adds nothing about the device identifier that the schema does not already say.

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?

Names a specific verb (dismiss) and a specific resource (the software keyboard on an iOS device), a combination that is unique among the ~250 sibling tools — no other entry touches keyboard visibility. An agent cannot confuse it with ios_send_keys, device_type, or ios_tap.

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 states the selecting condition ("if it is visible") and the prerequisite (an active iOS automation session), which tells the agent when this tool applies and what must already be true. It stops short of naming an explicit alternative or a when-not-to-use case, so it is strong context rather than full routing guidance.

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