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

No annotations are provided, so the description carries full burden for behavioral disclosure. It discloses the query semantics (substring vs glob), the meaning of 'truncated: true' (which prevents misinterpretation of partial results), and provides the walk behavior (on-device, avoiding list-by-list). It also hints at permissions (bundleId handling) and path results. The description could add more about side effects (none are expected) or error conditions, but the coverage is strong.

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 concise and well-structured. It opens with the primary purpose, immediately highlights the performance advantage, then details the query semantics, result handling, and important caveat (truncated). Each sentence contributes new information; there is no fluff or repetition. The mention of ios_file_list is a useful pointer that ties the tool into its family.

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?

Given the tool's moderate complexity (6 parameters, glob handling, truncation) and the absence of an output schema, the description is remarkably thorough. It covers the core behavior, parameter semantics, edge cases (glob detection, truncated), and even navigates the bundleId nuance. The description fully prepares an agent to call this tool correctly, including reporting expectations. The only possible gap is not describing the exact structure of the results, but that is mitigated by the clear path explanation.

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 description coverage is 100%, so the schema already documents all parameters. The description adds value by explaining the query semantics in more depth (case-insensitive substring, glob behavior) beyond the schema's brief description. It also clarifies the meaning of 'truncated' and the bundleId root selection, complementing the schema. However, the description doesn't detail every parameter (maxDepth, limit), so it's not a full 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 clearly states the tool's purpose: searching a subtree for files/folders by name. It specifies the verb ('Search'), resource ('files and folders'), and the scope ('subtree'), distinguishing it from list-only tools like ios_file_list. It also differentiates itself from generic device_file_find by being iOS-specific and emphasizing the on-device walk.

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 explicitly explains when to use this tool over alternatives: 'The walk runs on the device side, so this is the right way to locate a file — far cheaper than listing directories one by one.' This gives clear usage guidance. It doesn't mention when NOT to use it, but the positive guidance is strong. It also references ios_file_list for -comment.

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