cw_doctor

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

With no annotations, the description carries full burden. It usefully states the output shape ('each with a verdict and a remedy') and the scope, but never states that the check is read-only/non-destructive, nor whether the realtime MIDI and UIA click probes actively stimulate the host (potentially audible notes or synthetic clicks). That is a material undisclosed behavior for a diagnostic that touches live transports.

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 sentences, no filler. The scope enumeration comes first, and the when-to-use guidance follows immediately. Every clause earns its place.

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?

No output schema exists, and the description does supply the return shape informally (per-channel verdict plus remedy). For a zero-parameter diagnostic this is close to sufficient; the remaining gap is the absence of any note on side effects or runtime cost of the live MIDI/UIA probes.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly implies a parameterless, whole-system sweep rather than a targeted check.

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?

The description states a specific verb and resource ('Run a health check') and enumerates the exact scope: host, CakeScript, WM_COMMAND, surface bridge, realtime MIDI, UIA click. It clearly distinguishes itself from state-reading siblings like cw_status or cw_midi_status by being a cross-channel diagnostic, though it never names those siblings explicitly.

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?

'THE tool to run first after a SONAR upgrade' gives a concrete triggering condition, which is stronger than most usage guidance. However, no when-not conditions or explicit alternatives (e.g. cw_status, cw_benchmark, cw_latency for narrower checks) are named.

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