set_wireless_tx_power

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

With no annotations, the description carries the full behavioral burden and does so richly: it discloses the write guard (blocked unless MIKROTIK_ALLOW_WRITE=true), the dead-man lockout risk and that revert restores BOTH tx-power-mode and tx-power, the preview-vs-apply confirm semantics, and that it errors rather than creating a missing interface. The counterintuitive saturation behavior is also explained.

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 action and its forced side effect, and the length is justified by the tool's complexity and lack of annotations. It is slightly verbose, with the saturation example and the CCQ re-adaptation note occupying more space than strictly needed.

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, 6 parameters, and 0% schema coverage, the description covers the safety profile, the preview/apply flow, the write gate, the dead-man revert, and the error behavior. An output schema exists, so its note on the preview warning is supplementary rather than a gap.

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 largely does: tx_power (dBm), confirm (preview vs apply), arm_deadman/deadman_minutes (armed by default, revert behavior), and interface_name (errors if absent, never created) are all given meaning. Only device_name is left to inference, 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+resource ('Set a /interface/wireless interface's tx_power (dBm)') and adds the critical side effect ('forcing tx-power-mode=all-rates-fixed'), which distinguishes it from siblings like set_wireless_channel and set_wireless_tuning. An agent can identify the operation and its scope without opening the 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 routes the agent: use get_wireless_link_quality before/after to judge effect, and there is no universally correct power. It also spells out the confirm=False preview → confirm=True apply workflow, and names set_wireless_channel as the sibling with the same dead-man lockout behavior. When-to-use and alternatives are both covered.

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