arrangement_build_song

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

Beyond the annotations, the description discloses the refusal condition (existing clips in range), the atomic 'one undo step' behavior, and that audio tracks are reported as skipped. There is mild tension worth noting: clearing timeline clips via clear_existing is a removal, while destructiveHint is false, though the opt-in and refuse-by-default design makes this defensible rather than contradictory.

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?

It is dense and front-loaded with the core mechanism first, then constraints and the next step. The semicolon-chained clauses make it a single run-on sentence that takes a second read, but nearly every clause carries information.

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 mutating, non-idempotent tool with no output schema, the description covers the important behavior: input model, refusal condition, undo granularity, and skip reporting. It could say a bit more about what the call returns (e.g. which sections/markers were created) but nothing essential to correct invocation is missing.

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%, so the baseline would be 3, but the description adds genuine semantics the schema lacks: 'scene' is a scene row, 'bars' is the per-section length, 'markers' produces one marker per section, and clear_existing scopes removal from start_beat onward. That meaningfully raises it above the schema-only baseline.

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 gives a specific verb and resource (lay a song out on the timeline from session scenes) plus the mechanism: one scene row per section, MIDI clips copied and repeated to fill the row, a marker per section, TOMNIC patterns expanded to notes. This clearly separates it from siblings such as arrangement_place_clip (single clip) or arrangement_edit_clip.

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?

It provides concrete usage context: an example section plan (intro 8, verse 16, drop 16, outro 8), the precondition that the target range must be empty unless clear_existing is set, and the follow-up action 'Then arrangement.play.' It does not, however, contrast itself with alternative arrangement-building routes like agent_arrange_timeline or arrangement_place_clip.

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