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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the safety and side-effect profile is covered. The description adds useful domain disambiguation but no behavior beyond annotations, such as what "opening" does, authentication needs, or what the agent should expect to happen next.

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 compact sentences: the primary usage is front-loaded and the exclusion follows immediately. There is no superfluous wording, and both sentences contribute to correct selection.

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 no input parameters, an output schema, and rich annotations, the definition is nearly complete for a simple open/browse tool. The main remaining gap is that it does not explicitly distinguish itself from the report-oriented siblings despite mentioning reporting as a use case.

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 zero parameters, so there are no parameter semantics the description needs to compensate for. The baseline for a no-parameter tool is 4.

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 uses a specific verb and resource ("open CleanApp") and adds related actions such as reporting a problem or browsing the miniapp. It is distinguishable from non-CleanApp tools, though the reporting and browsing phrasing overlaps conceptually with sibling report tools without naming them.

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 when-to-use triggers (open CleanApp, report a problem, browse the miniapp) and clear exclusions (household cleaning advice, disk-cleaning tasks). It does not name sibling report tools as alternatives, so routing between this and cleanapp_prepare_report or cleanapp_submit_report is left somewhat implicit.

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