add_audio_section

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

Annotations already flag non-read-only, non-idempotent, non-destructive. The description adds real behavioral context: find-or-add track logic, the conditional section insertion, placement at playback range start, and the saved/save_error state. It does not contradict the idempotentHint=false annotation, since repeated calls can still add sections.

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?

Front-loaded with the core action, followed by the reuse rule and the conditional section rule. The Returns block is long but earns its place as the substitute for a missing output schema. No filler sentences.

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?

With no output schema, the inline Returns breakdown fully documents track_added, sound_loaded, section_added, section_count, saved and save_error. Combined with the dependent-call hint for audio_track_index, an agent has enough to call and chain this correctly; only the explicit alternative-tool routing 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 already 100%, but the description adds meaning beyond the schema's terse 'content path' note: sound_path only produces a section if it loads a USoundBase, and the section lands at the playback range start. It also explains that the returned audio_track_index feeds the volume/pitch tools.

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+resource: 'Adds (or reuses) a root audio track on a Level Sequence and optionally a section.' The add/reuse and optional-section semantics are clear, and the tool is distinguishable from siblings like set_audio_track_volume or add_camera_cut_track. It does not, however, name or route away from any sibling.

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?

Usage context is implied: reach for it when a sequence needs a root audio track, and it will reuse an existing one rather than duplicating. There is no explicit when-not or an alternative tool named, so the agent must infer boundaries from the description alone.

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