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

Annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) already establish the safety profile, and the description adds substantial context beyond them: the >8 KB files stored in responseCache (a meaningful side-effect of a read operation), the plist→text→binary decode fallback with contentType, path-traversal rejection, per-mode return shapes, and specific error conventions (InternalError with install suggestion). It also discloses the macOS plutil dependency.

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 document is long but proportionate to a 4-mode tool, and it is rigorously structured: one-line summary up front, followed by What-it-does, Parameters, per-mode behavior, Returns, code examples, Error Handling, and Notes. Headers, bullets, and TypeScript call examples make it highly scannable for an agent. Some redundancy exists between the parameter list and mode sections, but for LLM recall, prose-plus-example repetition 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?

With zero schema descriptions and no output schema, the description must be self-sufficient — and it is. It covers expected inputs per mode, mode-specific return fields, error cases, edge cases (large files, unreadable plists, path traversal), and operational caveats (macOS-only plutil, Keychain exclusion). The only mild gap is the generic top-level return shape ('{ mode, bundleId, success, ... }'), but each mode's specific fields are already described.

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 0%, so the description carries the full burden — and it delivers. Each of the 5 parameters gets semantic meaning: bundleId format example, mode enum explained across four detailed sections, udid default ('Defaults to booted device'), path semantics per mode (subdir for ls vs file for cat), and depth default (3). This fully compensates for the bare schema.

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 opening line — 'list files, read file contents, inspect UserDefaults, and locate Core Data stores inside an iOS simulator app's data container' — states a specific verb+resource scope that clearly differentiates it from siblings like simctl-get-app-container (path resolution only) and simctl-list (device listing). The four modes are each named and their distinct purposes enumerated.

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 rich context: it states the tool wraps get_app_container 'without needing to know the raw CoreSimulator path' (implying the alternative raw-path workflow), explicitly scopes out Keychain, and routes large-file retrieval to 'the cache tool' via cacheId. However, it never explicitly names siblings as alternatives (e.g., 'if you only need the container path, use simctl-get-app-container'), so the when-vs-alternative guidance is implied rather than stated.

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