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

With no annotations, the description fully discloses behavior: return fields (deleted, failed), 'force' flag semantics, destructive nature with no undo, and the refusal of camera photos/videos with a detailed explanation of the media-database inconsistency. It also notes that user-pushed files are always deletable, covering edge cases comprehensively.

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 information-dense with no filler, but slightly long relative to its simple core action. Each sentence contributes unique value (recursion, use case, return values, force, destructive warning, media refusals), balancing completeness without being bloated.

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 destructive tool with no output schema, the description is remarkably complete: it covers return format, failure handling, use case, destructive implications, and unusual edge cases (camera media refusals). It addresses both what happens on success and failure, plus the underlying rationale for refusals.

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?

The input schema covers all parameters at 100%, so the baseline is 3. The description adds some value by linking 'bundleId' root selection to ios_file_list and clarifying 'force' behavior, but it does not substantially extend the parameter meanings beyond what the schema already states.

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 uses a specific verb ('Delete') and resource ('file or directory tree on an iOS device'), explicitly noting recursive directory removal. It clearly distinguishes from siblings by referencing ios_file_list for root selection and emphasizing the use case of clearing cached state between test runs.

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 context for when to use the tool ('clearing an app's cached state between test runs') and references ios_file_list for consistent bundleId root selection. It does not explicitly name alternatives for deletion (e.g., device_clear_app_data), but the intended use and tie to ios_file_list provide strong guidance.

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