app_list

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

No annotations are provided, so the description bears full responsibility. It implies a read-only enumeration but does not explicitly state non-destructiveness or potential side effects. The behavior is inferred from the listing nature.

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?

Two well-structured sentences: first states purpose and output, second provides usage hints. No redundancy, front-loaded with key information.

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?

The description covers the tool's core function and parameter usage but omits the udid parameter entirely. No output schema exists, so the description partially compensates by listing returned fields (identifier, name, pid), but could be more comprehensive.

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?

All parameters have schema descriptions (100% coverage), so the description adds marginal value. It reinforces userFacing's default filtering and runningOnly's purpose but does not clarify the udid parameter or add new detail about query behavior.

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 verb 'Enumerate' and the resource 'apps' with output fields (identifier, name, pid). It differentiates from sibling 'process_list' by focusing on apps and mentioning default filtering. However, it does not explicitly compare to similar siblings.

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 explicit guidance on parameter usage: default userFacing=true filters noisy services, runningOnly for live apps, query for substring matching. It does not, however, advise when to use app_list over other tools like process_list.

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