set_poe_out

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 declares this is a WRITE tool gated behind MIKROTIK_ALLOW_WRITE=true, explains the confirm preview/apply flow, and specifies failure behavior (errors without changing anything if the interface is missing or non-PoE, never creates or coerces). This is exactly the behavioral context an agent needs for a 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 core action and command form, then the idiomatic use case, then the safety gate. Every sentence earns its place, though it runs a bit long and the command syntax is arguably redundant for an agent that must call the tool rather than a shell.

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 no annotations and a 0%-covered schema, the description supplies the write gate, the confirm lifecycle, the enum values, the canonical use-case procedure, and failure modes. With an output schema present it need not explain returns, so nothing essential 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 description coverage is 0%, so the description must compensate. It does: it defines the allowed poe_out values (auto-on, forced-on, off), explains confirm's default-False preview semantics, and describes error conditions for interface_name. device_name remains undocumented, which is the only gap.

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+resource: set a PoE-capable ethernet port's PoE output mode, including the exact RouterOS command form. It is clearly distinguishable from its closest sibling poe_status (which only reads), and from enable_interface/disable_interface which act on the interface rather than PoE power.

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 states the primary use case (resetting a locked-up PoE device) with the exact procedure: off with confirm=true, wait for power-down, then auto-on. It also explains when to call confirm=False vs confirm=True, leaving nothing to inference.

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