setup_ducking

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

There are no annotations, so the description must carry the behavioral burden. It does disclose that the tool computes 4 keyframes per window plus boundary keyframes and follows a specific time convention. However, it does not mention whether existing keyframes are replaced, whether the clip must be selected or targeted, or what happens on failure, leaving important mutation behavior undisclosed.

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?

The description is four sentences, front-loaded with the main purpose, and contains no redundant restatements of the tool name. The only minor weakness is the insider reference to 'Sprint 3', which is not meaningful to an agent without that context, but it does not add significant bloat.

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 the tool's moderate complexity, the description covers the algorithm, the alternative approach, and the time convention. The schema fully documents all parameters, and although there is no output schema, the description gives enough behavioral context for an agent to call the tool correctly. The main omission is the effect on existing keyframes, but this is not critical enough to drop below a 4.

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 is 3. The description adds value beyond the schema by explaining how fadeSeconds maps to pre-fade/duck-in/duck-out/post-fade keyframes and by stating that times are clip-source-time absolute, which clarifies the meaning of startTime, endTime, clipStartTime, and clipEndTime.

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 resource: a 'high-level wrapper around add_audio_keyframes' that 'builds a ducking curve from a base level + ducking windows.' It clearly distinguishes itself from the lower-level add_audio_keyframes sibling by positioning itself as the higher-level convenience tool.

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 explicitly names the underlying alternative (add_audio_keyframes) and states that it replaces the manual '8 keyframes per video' pattern, giving clear direction on when to choose this tool. It could be stronger by stating explicit conditions to prefer manual keyframing, but the usage context is clear.

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