Generate

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

Annotations already declare destructive=true, readOnly=false and non-idempotent, so the safety profile is covered. The description adds genuinely new behavior: kind-specific parameters are validated before any track is added, and the operation either creates a track or replaces audio within a range. It omits the practically important details — what happens on validation failure, whether a partial write is possible, and which parameters are mandatory per kind.

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 the capability statement front-loaded and the mode/validation caveats following. The slash-delimited enumerations are dense but readable, and there is no filler. It could be split slightly for scannability, but nothing is wasted.

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 17-parameter destructive generator, the definition leaves the most consequential gap open: no per-kind parameter applicability or required-combination guidance. An output schema exists so return values need no explanation, and annotations cover the destructive nature, but the kind-to-parameter mapping is the single thing this description had to supply and does not.

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 only 12% across 17 parameters, so the description carries the burden of explaining them — and it does not. It names the kind values and mentions 'kind-specific parameters' without mapping any parameter to a kind (e.g. frequency/waveform to tone, noiseType to noise, tempo/swing/beatsPerBar/clickSound to rhythm), which is exactly the information an agent needs to avoid a validation error. The only real parameter insight offered is that track drives create-vs-replace and duration comes from the selection.

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 opens with a specific verb and an enumerated set of generated resources ('tone/noise/silence/chirp/rhythm'), plus the two output modes (new track vs. replacing a range of an existing track). That is far more informative than 'Generate'. It stops short of distinguishing itself from sound-producing siblings such as audacity_effect or audacity_noise_profile, but the enumerated kinds make the resource scope unambiguous.

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?

There is useful implied guidance: the tool draws its duration from the current time selection, and the new-track-vs-replace decision is signalled by the track parameter. However, no when-to-use/when-not conditions are stated, and no alternative is named for cases where the agent should be applying an effect or generating into a different context. The selection-dependency is the only real routing hint.

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