device_queue_flush

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the destructive nature is covered. The description adds the useful severity detail that ALL queued downlinks are discarded rather than a subset, which goes slightly beyond the annotation, but it does not add context on irreversibility, prerequisites, or effects on in-flight messages.

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 entire useful content fits in one sentence with a front-loaded verb and zero wasted words. It is appropriately minimal for a tool this simple.

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 tool is simple (one parameter) and the output schema exists, so return values need no explanation. However, the description still leaves gaps: no confirmation of the operand semantics, no caution about the destructive effect beyond the annotation, and no context about when clearing the whole queue is appropriate. Adequate for a trivial tool, but not 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?

With 0% schema description coverage, the description should compensate by explaining dev_eui, but it never mentions the parameter at all. The name dev_eui is self-descriptive and consistent with sibling tools (device_get, device_delete, device_enqueue), which mitigates the gap somewhat, but the description itself adds zero 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 uses a specific verb ("Discard") with a specific resource ("queued downlink") and a clear scope ("every"), so the agent knows exactly what is acted upon. It implicitly differentiates from sibling tools like device_enqueue and device_queue_get, though it never names them explicitly.

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?

Usage is implied — if an agent wants to clear a device's outbound queue, this is the tool — but there is no explicit when-to-use guidance, no exclusions, and no mention of alternatives such as device_enqueue or device_queue_get. The description relies on the tool name and sibling list to convey context.

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