cw_enable_midi_port

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

With no annotations, the description carries the load and does so well: it discloses that the tool writes a config file, that it is idempotent, and that the effect is deferred until restart/dialog apply. It omits whether existing entries are preserved or how failure is reported, which would complete the picture for a file-mutating 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?

Two tight sentences with nothing wasted; the mechanism and the outcome are front-loaded and the deferral caveat follows immediately.

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 three-parameter file-writing tool with no annotations and no output schema, the description covers mechanism, safety-relevant idempotency, and timing of effect. Only minor gaps remain (validation of the port name, behavior on write failure) and none block a correct call.

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 67%: 'port' and 'backup' are documented in the schema, but 'section' has an enum with no description anywhere. The description adds no parameter-level meaning, so the baseline 3 for partially documented params is right.

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 ('Enable a MIDI port in SONAR') and the exact mechanism ('by writing TTSSEQ.INI'), plus the outcome ('the MIDI transport reaches SONAR'). That mechanism clause implicitly separates it from UI-driven siblings like cw_midi_devices or cw_ui_recipe.

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 an explicit when-not: the change is not live in the current session and only applies at startup or when the MIDI Devices dialog is applied, which steers the agent away from expecting immediate effect. It stops short of naming a sibling to use instead when a live change is wanted.

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