setup_ducking

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

With no annotations provided, the description carries the transparency burden well. It discloses the keyframe generation algorithm (4 per window, plus boundary keyframes), the base level + window model, and the clip-source-time convention. It stops short of stating whether existing keyframes are overwritten or what side effects occur, but the core behavior is well communicated.

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?

Three dense, purposeful sentences: purpose first, then algorithm, then convention. Every sentence contributes unique information with no redundancy or fluff.

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 tool with nested parameters, no output schema, and no annotations, the description is thorough. It covers the algorithm, defaults, edge case (empty windows), and time conventions. Missing explicit preconditions or error scenarios, but the overall context is strong enough for an agent to select and invoke correctly.

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?

Although schema coverage is 100%, the description adds substantial meaning: it clarifies how baseDb and duckingWindows interact, explains the fallback for clipEndTime, defines defaults for fadeSeconds and clipStartTime, and details the time convention. This goes well beyond the schema's field descriptions.

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 uses a specific verb ('builds') and resource ('ducking curve'), and immediately distinguishes itself from add_audio_keyframes by calling itself a 'high-level wrapper.' This makes the tool's purpose unmistakable and differentiates it from its key 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?

It explicitly frames the usage context: automated ducking versus the manual '8 keyframes per video' pattern from Sprint 3. It also ties the time convention to add_audio_keyframes, helping the agent know when to choose this tool. It lacks explicit exclusions or alternatives beyond the manual pattern, but the guidance is clear.

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