clear_dns_cache

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

With no annotations, the description carries the full burden and does so: it discloses that only cached answers are cleared (never config), that results repopulate on next resolution, that the operation is confirm-gated, and that it is blocked without the write env flag.

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?

Content is front-loaded (what it does, then safety, then the guard/confirm mechanics) and every sentence earns its place. Slightly verbose with parenthetical asides and line breaks, but no filler.

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?

An output schema exists, so return values need not be explained. Given the guard requirement, the confirm flow, and the benign-but-gated nature of the write, the agent has everything needed to invoke this correctly.

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?

Schema coverage is 0%, so the description must compensate, and it does for the key parameter: confirm=False previews while confirm=True executes, including the default. It implies no-argument clearing of the whole cache, and device_name is self-evident for a multi-device server.

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?

States a specific verb and resource ('Flush the device's DNS resolver cache') and even names the underlying endpoint `/ip/dns/cache/flush`. An agent can distinguish this from the read-only sibling `dns_cache` without opening a schema.

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?

Explicitly describes the two-step flow: call with confirm=False (default) to preview cached-entry count, then confirm=True to flush. It also states the prerequisite that the server must run with MIKROTIK_ALLOW_WRITE=true, so when-not-to-use is covered.

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