add_netwatch

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

No annotations are provided, so the description carries the full burden, and it does: guarded write blocked unless MIKROTIK_ALLOW_WRITE=true, dry-run default, does-nothing-on-duplicate error path, and an explicit security rationale for the deliberately absent up-script/down-script capability. This is disclosure well beyond a typical mutation tool.

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-loaded with the purpose and command, then clearly partitioned into SECURITY and WRITE sections, so a skimming agent can find the guard and confirm rules quickly. It is longer than strictly necessary — the security paragraph restates the script restriction twice — but every section carries actionable information.

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 mutation tool with an output schema already present, the description supplies everything an agent needs before calling: prerequisites, confirm workflow, duplicate handling, and the security boundary. Return-format details are correctly left to the output schema.

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 description coverage is 0% across five parameters, so the description must compensate; it explains `host` (plain IPv4/IPv6), `interval` (RouterOS duration with concrete examples "10s"/"00:00:10"), `comment`, and fully documents `confirm`'s preview/apply semantics. Only `device_name` goes unexplained, a minor gap given it is a required target selector.

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?

Opens with a specific verb+resource plus the underlying CLI command (`/tool/netwatch add`), immediately distinguishing it from the read-only `netwatch` sibling that also appears in the tool list. An agent knows exactly what gets created (a Netwatch host monitor) and against what input (a host address).

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?

Explicit routing: use this to create a monitor, use the read-only `netwatch` tool to inspect script presence, and configure up/down scripts manually on the device rather than through this tool. It also states the two-step invocation contract (confirm=False for preview, confirm=True to apply), which is the key usage decision for this tool.

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