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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new context: that listing does not launch an app and that account-bound computer:read OAuth is required. It stops short of describing what is returned (app names, bundle identifiers, running status), which matters somewhat because no output schema exists.

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?

Three tight sentences: purpose first, then alternatives, then prerequisite. Every clause carries information an agent needs and nothing is repeated from the name or annotations.

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 zero-parameter read tool with no output schema, the description supplies purpose, alternatives and auth scope, which is close to sufficient. The one remaining gap is the shape of the returned list, which an agent must discover by calling it.

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 tool takes no parameters, so the schema is complete by definition and there is nothing for the description to disambiguate. Baseline 4 applies; the description neither adds nor omits parameter meaning.

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 installed macOS applications') and immediately scopes it with 'without launching one', which clarifies the read-only nature. The distinction from exza_launch_desktop_app and exza_list_desktop_windows is made explicit, so an agent can select this tool without inspecting sibling schemas.

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?

It gives explicit routing guidance: use exza_list_desktop_windows for visible windows and exza_launch_desktop_app to start an app. This covers both the when-to-use case and the nearest confusing alternatives by name.

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