set_ntp_servers

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 well: it discloses the write guard, the two-step preview/apply flow, that only the server list mutates, and the ROS6 vs ROS7 divergence including dropping extras beyond two entries and hostname folding into `server-dns-names`.

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?

Front-loads the purpose, then the write guard, then the confirm flow, then generation-specific behavior. Dense but every paragraph earns its place; slightly heavy, but proportional to the tool's real complexity.

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 guarded write tool with an output schema (so return values need no prose) and 0% schema coverage, the description covers safety, invocation flow, cross-generation differences, and references the docstring for full mapping rules. Nothing an agent needs to call it correctly is missing.

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; it explains `servers` (one or more IPv4/IPv6 addresses or hostnames) and `confirm` (default False = preview, True = apply) thoroughly. Only `device_name` is left implicit, which is minor.

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 precise verb and resource ('Set the NTP server(s) a device syncs its clock against') and even names the underlying RouterOS path `/system/ntp/client`. It is easily separable from read-only siblings like `ntp_client` and `system_clock`.

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?

Gives clear when-to-use mechanics: blocked unless MIKROTIK_ALLOW_WRITE=true, call with confirm=False for a preview, then with confirm=True to apply. It also excludes a neighboring behavior ('never enables/disables the NTP client itself'), though it does not name an alternative tool by name.

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