capcut_normalize_audio

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It implies a mutation (normalization changes existing volumes) and scopes to a track, which is useful, but it never discloses that this modifies the draft, how 'dialogue/voice' segments are identified versus other audio, whether non-voice segments are left untouched, or whether the change is staged pending capcut_save/capcut_discard. These are material unknowns for an agent predicting side effects.

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?

A single front-loaded sentence with an active verb and a tight complement ('across all segments on a track') with zero wasted words. It is appropriately structured for readability, but the brevity borders on under-specification: for a 3-parameter mutation tool, one sentence is near the lower bound of adequate size.

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?

Given no annotations, no output schema, and a draft-edit workflow implied by siblings (capcut_save, capcut_discard), the description is incomplete. It fails to explain when this is preferable to audio-effect/ducking tools, what the tool returns (no output schema exists to fill this in), how voice segments are detected, and the staged-edit behavior. The high-level purpose is clear, but an agent lacks critical operational details needed to invoke it correctly and safely.

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 67% (trackIndex and targetVolume documented), leaving the required 'draft' parameter entirely undocumented, and the tool description adds nothing to compensate — it does not mention draft, trackIndex, or how targetVolume multiplier semantics interact with normalization. The description's phrase 'normalize... volume' loosely aligns with targetVolume, but the required parameter's meaning is a genuine gap that neither schema nor description fills.

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 has a specific verb ('Normalize'), a clear resource ('dialogue/voice volume across all segments on a track'), and a defined scope. The unique verb makes it distinguishable from audio-related siblings like capcut_set_audio_fade, capcut_apply_audio_effect, and capcut_auto_duck_bgm, though it never explicitly names or contrasts them. Since no sibling performs normalization, an agent can likely select it correctly, but the differentiation is implicit, not stated.

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?

The description provides no guidance on when to choose this tool over its audio alternatives — nothing about when normalization is appropriate versus auto-ducking, fading, or applying audio effects, and no exclusions or preconditions. The closest siblings (capcut_auto_duck_bgm, capcut_set_audio_fade) operate in a similar 'adjust audio levels' space, so the lack of routing guidance is a real gap.

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