groove_generate

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

With no annotations, the description carries the full burden and does meaningful work: it declares the write scope ('writes only a content-addressed local artifact'), states it never touches the Live host, asserts determinism, and names failure classes (rights, bounds, unknown transform axes fail explicitly). It still omits whether the run is expensive, whether artifacts are immutable/deduplicated, and what a successful call returns.

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?

Purpose is front-loaded, followed by side effects, a call example, and failure modes in four tight lines with no filler. Each sentence adds distinct information for an agent deciding whether and how to call it.

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 7-parameter nested-object tool with no annotations and no output schema, the description covers purpose, side effects, an example and failure modes, but leaves three parameters and the entire return value (presumably an artifact id the agent needs for downstream groove_apply/groove_compare calls) undocumented. Adequate, but gaps remain that matter for chaining.

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% across 7 parameters (5 required, one nested object), so the description must compensate. The worked example usefully pins down the shapes of source (an object keyed by artifact_id) and transforms (a map), but provider, schema_version and reference_artifact_ids are never explained, and the enum choice between deterministic and neural goes unmentioned despite the description's blanket claim of determinism.

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: 'Create a deterministic derived artifact in the local content store.' An agent can distinguish this from read/inspect siblings such as groove_search, groove_evidence and groove_compare. It does not, however, differentiate itself from the other generators (music_generate_drum_groove, music_generate_bass, groove_apply), leaving ambiguity about which generation tool 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?

There is no explicit when-to-use guidance, no prerequisites (e.g., must a source artifact exist first?), and no named alternative among the many groove_* and music_generate_* siblings. The 'never calls Live' remark constrains scope but is not usage guidance for choosing this tool over groove_apply or music_generate_drum_groove.

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