queue_purge

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

With no annotations provided, the description carries the full burden. It discloses irreversibility beyond a 60-second undo window, the requirement for the 'destructive' scope, and the need for confirm=True. This goes beyond a simple 'clears scans' and informs the agent about safety and irreversible side effects. It does not describe potential side effects like impact on scheduled scans or data, but given the single-purpose nature, this is sufficient.

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 two sentences with no filler. The primary action is stated first, followed by critical caveats (irreversibility, scope, confirmation) in a logical order. Every sentence adds essential information, and nothing is redundant.

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 core action, safety requirements, and the one parameter. It does not explain return values (no output schema, so not required) or further consequences, but for a single-purpose destructive operation, it provides all necessary information to call the tool correctly. It could mention that it clears both queued and running scans, which it already does, so it is near-complete.

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 input schema has only one parameter, confirm, with no description coverage (0%). The description compensates fully by explaining that confirm=True is required to actually perform the action. This directly clarifies the parameter's role and the tool's behavior without confirmation. This is a high-value addition beyond the bare boolean 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 description states a specific verb (clear), a specific resource (every queued/running scan), and the scope (this key's tenant). It clearly distinguishes itself from siblings like queue_cancel_task (which targets a single task) and queue_pause/resume (which pause/resume rather than clear). The phrase 'for this key's tenant' adds a scoping detail that prevents confusion with tenant-wide operations.

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 clearly implies when to use this tool (when you want to clear all queued/running scans) and explicitly references queue_undo_purge for the undo window, telling the agent about an alternative for reversal. However, it does not explicitly state when not to use it or contrast it with other queue management tools (e.g., queue_cancel_task for a single task). It provides clear context but lacks explicit exclusions or alternative routing beyond the undo case.

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