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

Since no annotations are provided, the description carries the full burden. It notably explains the behavioral difference from backspace-based clearing ('reliable for any field length'), which is useful behavior insight. It also discloses the auto-start session behavior. It doesn't mention whether the clear is reversible or what happens to the clipboard, but the core behavior is well disclosed. With no annotations available, this is strong but not exhaustive.

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 compact (2 sentences plus a pattern hint) and information-dense. Everything included is useful: purpose, reliability comparison, usage modes, pattern, and session requirement. Slightly dense but all content earns its place.

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 simple action tool with only 4 params (1 required), a clear usage pattern, and full schema coverage, this is complete. It covers selection mode (focused vs labeled), the workflow context (before send_keys), and session requirements. No output schema exists, so no return-value documentation is needed, and the behavior is simple enough that what's provided suffices.

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 schema documents all parameters. The description adds context about the label parameter (omit vs pass behavior) and type/strategy usage ('used only when label is given'), which enriches schema meaning. However, it doesn't add much detail beyond that; strategy enum values are self-explanatory in the schema. Baseline 3 is appropriate since 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 is specific: 'Clear a text field on an iOS device using the native element-clear command.' It clearly states the verb (clear), the resource (text field on iOS device), and the method (native element-clear command). It distinguishes from siblings by noting reliability 'unlike sending backspaces' and its focus-field behavior differs from the generic device_clear_text.

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 explicit when-to-use guidance: omit label to clear the focused field (with instruction to tap first), pass label to target a specific field. It provides a clear usage pattern ('Pattern: tap field → ios_clear_text → ios_send_keys'), which is actionable and distinct from the generic device_clear_text sibling. It also notes session requirements.

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