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

With no annotations, the description carries the burden of behavioral disclosure. It explains the important edge case of unreadable entries (type: null plus error), which prevents a single bad child from hiding the listing. It does not discuss auth, permissions, or side effects, but for a read-only listing tool, the key behavioral traits are covered.

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?

Four well-organized sentences. Each sentence earns its place: purpose/return, bundleId guidance, depth guidance, and error behavior. No filler or repetition of schema details.

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 4-parameter tool with no output schema and no annotations, this description covers purpose, parameters, return set, and error handling. It tells the agent exactly what to expect and how to choose bundleId. The only minor addition could be an example invocation, but the current description is sufficiently complete.

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 baseline is 3. The description adds valuable context beyond the schema: bundleId scopes to an app's database/caches/logs vs shared media, and depth controls recursion. This meaningfully supplements the schema descriptions, especially for bundleId and remotePath's root semantics.

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 specific verb and resource: 'List files and directories on an iOS device.' It clearly states the return payload (name, type, size, modification time) and differentiates from sibling tools like ios_file_stat (single file stats) and device_file_list (generic) by specifying iOS context and the distinction between app container and shared media browsing.

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 provides clear guidance on when to include bundleId (to browse an app's own container) versus omitting it (shared media), and when to increase depth for recursion. It implicitly distinguishes from other file tools by focusing on listing behavior, but does not explicitly name alternative tools or state exclusions.

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