cw_latency

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

With no annotations, the description carries the full burden and does disclose default behavior and the timeout rationale for skipping the plugin-read stage. However, it never states whether profiling 'MIDI sends' actually transmits MIDI (a side-effect question for a diagnostic tool) or whether the operation is safe and non-destructive.

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, front-loaded with what is profiled and immediately followed by the one decision an agent must make. No filler and no repetition of the parameter name.

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 single-optional-parameter diagnostic with no output schema, the description covers purpose and the one behavioral trap (timeout). It is slightly short on what the returned latency figures look like, but an agent can call it correctly from what is here.

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 100% and the parameter already documents 'Adds 10s+; skipped by default.' The description reinforces which stage is slow and why it is off, but adds no syntax or interaction detail beyond the schema, so the baseline 3 applies.

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?

Names the resource precisely — a per-operation latency profile covering bridge round trips, menu commands, MIDI sends, and plugin reads — so the agent knows this measures timing, not state. It only indirectly differentiates itself from cw_benchmark by referencing it as an analogy rather than stating how the two split the workload.

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 default decision is well covered: plugin reads are off unless explicitly requested, with the reason given. But there is no explicit guidance on when to reach for cw_latency versus the many sibling diagnostics (cw_benchmark, cw_timing, cw_status, cw_doctor), leaving the choice to inference.

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