Command

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

The annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered. Beyond that, the description adds genuinely non-obvious behavioral context: operations apply to the current selection, Set* commands silently depend on track selection, and NoiseReduction will fail without a captured profile. It still does not say whether effects are undoable or what happens when params are invalid, which keeps it from a 5.

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?

Three compact sentences with the primary action front-loaded, followed by parameter sourcing and then prerequisites. The elided effect list is short and illustrative rather than padded. Minor inefficiency in mixing the effect catalogue, the Set* caveat, and the NoiseReduction caveat into one run-on block.

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 two-parameter but enormously broad dispatcher, the description covers the essentials an agent needs to attempt a call: scope (selection), parameter lookup path (audacity_describe), and two hard prerequisites. Gaps remain around failure modes, undoability, and whether non-Selection commands (Export2, GetInfo, Import2, CompareAudio) behave differently, which matter given the destructive, open-world annotations and the absence of an output schema.

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% for both parameters, and the command enum alone has dozens of values with wildly different parameter sets, so the description must compensate. It does the right thing by stating that parameters follow Audacity's own list and pointing at audacity_describe, and it flags one specific case (NoiseReduction needs a profile), but it conveys no actual per-command parameter meaning, format, or required/optional structure beyond that pointer.

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 scope: run a catalogue scripting command or effect on the current selection, with an illustrative list of effects (Amplify, Compressor, Limiter, ...) and the note that it also covers native Set* commands. That is a clear, concrete purpose, but it never distinguishes this catch-all dispatcher from overlapping siblings such as audacity_effect, audacity_auto_duck, or audacity_fade, so an agent cannot tell from the text alone which entry point to pick.

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?

Useful precondition guidance is present: Native Set* setters act on selected tracks and require calling audacity_select first, and NoiseReduction requires a captured profile. However, there is no statement of when this tool should be preferred over the many effect-specific siblings, and no exclusion of cases where it would be the wrong choice, leaving the choice largely to inference.

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