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

Beyond the idempotentHint and destructiveHint annotations, the description discloses meaningful behaviors: graceful shutdown, handling of 'already shutdown' without error, batch operation efficiency, internal state tracking, and a safety-check relationship with device deletion. These details help an agent predict side effects and downstream requirements.

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 well-structured with Overview, Parameters, Returns, Examples, Related Tools, and Notes sections, making it easy to scan. It is somewhat verbose for a single-parameter tool, and some notes repeat earlier content, but every section adds practical value and nothing feels irrelevant.

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 simple one-parameter tool, the description is complete: it documents the only parameter, describes return information, provides examples for all valid value categories, notes edge-case handling, and explains the relationship to deletion and state tracking. With no output schema present, the Returns section helps fill that gap.

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 schema provides no description coverage (0%), but the description fully compensates by explaining that deviceId accepts a UDID, 'booted', or 'all', and illustrates each value with concrete examples. This is exactly the semantic information an agent needs and would not get from the schema alone.

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 'Shutdown iOS simulator devices' and elaborates with a specific verb and resource: 'Gracefully shuts down one or more iOS simulator devices.' It clearly distinguishes the tool from siblings like simctl-boot and simctl-list by naming its exact operation and supported targeting modes.

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 Related Tools section explicitly connects simctl-shutdown to simctl-boot, simctl-list, and simctl-delete, and notes it is 'Required before device deletion.' It also gives practical guidance like using 'booted' for quick shutdown of all running simulators. It stops short of explicit when-not-to-use exclusions, such as distinguishing shutdown from simctl-terminate, so it is slightly below a perfect score.

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