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

With no annotations, the description carries full responsibility and excels: it discloses that the walk runs device-side (performance implication), explains query semantics (case-insensitive substring vs glob), reveals that results include both relative and absolute paths, and, importantly, explains the `truncated: true` flag and how to report it. This goes well beyond simple 'search'.

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 yet rich: five sentences logically ordered—purpose, efficiency rationale, query semantics, result contents, truncation behavior, and cross-reference. Every sentence adds necessary information without redundancy. It is front-loaded with the core action and scopes the tool immediately.

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 6-parameter tool with no output schema, this description is remarkably complete. It covers the intended use case, performance context, query syntax rules, result format, truncation behavior, and how the bundleId root selection aligns with a sibling tool. There is no significant gap that would leave an agent confused about what to expect.

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% and the schema already documents all parameters. The description adds value by clarifying that `query` is case-insensitive (not in schema) and elaborating on the truncation semantics tied to `limit`. It does not fully expand on `maxDepth` or `udid`, but those are self-explanatory in the schema. The added nuances justify a 4.

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 opens with a precise verb+resource+scope: 'Search an iOS device subtree for files and folders whose NAME matches a query.' It clearly distinguishes itself from sibling ios_file_list by positioning this as the efficient way to locate files ('far cheaper than listing directories one by one'), and the later reference to ios_file_list reinforces the family relationship.

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?

It gives explicit when-to-use guidance ('the right way to locate a file') and contrasts with listing directories step by step, which points to ios_file_list as the alternative. It also references the consistent bundleId selection. However, it does not fully spell out when NOT to use the tool (e.g., when you need to enumerate a directory without name filtering), so it stops short of a full 5.

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