ae_build_smart_edit

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

With no annotations, the description carries the behavioral burden and does disclose the key side effects: importing footage when a path is provided and creating a sequential edit comp. It also reveals the selection behavior (silence/dead air, not random) and a negative behavior (no subtitle bars). It does not state overwrite behavior for an existing comp name, but the core mutation and output type are explicit.

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 short sentences with no filler. The primary action is front-loaded, followed by two behavior notes that each earn their place.

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 no annotations and no output schema, the description supplies the essential prerequisites (segments from ae_analyze_cuts), the optional import behavior, the cut criterion, and a notable non-goal. It only leaves minor ambiguity about how to provide footage when it is not already in the project and about the exact return or comp naming behavior.

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?

The description adds practical meaning over the schema: 'optional if already in project' clarifies the path/footage_name choice, and 'KEEP segments from ae_analyze_cuts' reinforces what segments must contain. It does not elaborate on comp_name or frameRate, but these have defaults and the schema already covers 60% of parameters.

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 names a specific action (build a sequential edit comp), the input source (KEEP segments from ae_analyze_cuts), and the processing behavior (cuts on silence/dead air). It also distinguishes itself by stating it does not add subtitle bars, separating it from related editing and subtitle tools.

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 tells the agent that importing is optional when footage is already in the project, implying when path vs footage_name should be used, and it positions the tool as the follow-up to ae_analyze_cuts. It does not explicitly name alternatives such as ae_build_youtube_edit, but the silence/dead-air criterion and 'no subtitle bars' note provide clear context for selection.

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