ae_analyze_cuts

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

With no annotations, the description carries the full burden. It discloses the ffmpeg dependency and that it returns segmentation results, but it doesn't state whether the operation is non-destructive, how results are structured, or what happens if ffmpeg is missing or fails. The behavior is mostly clear but not fully transparent.

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 concise sentences: function first, then usage context, then alternative. Every sentence earns its place, with no wordiness or repeated schema content.

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 an analysis tool with no output schema, the description gives a clear sense of what it returns ('KEEP segments vs silence'), a prerequisite ('Requires ffmpeg on PATH'), and a routing option. It could specify the return format more precisely, but it's largely complete for selecting and invoking the tool.

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 100%, so the schema already documents all 5 parameters with clear descriptions. The description adds no parameter-specific meaning, which matches the baseline 3 for fully-covered schemas.

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 verb ('Analyze'), a resource ('video'), a concrete method ('ffmpeg silencedetect'), and an explicit output ('KEEP segments vs silence to remove'). It also differentiates from speech-aware siblings by naming ae_transcribe_video and ae_transcript_to_cuts, so agents can clearly distinguish when to use this 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?

Provides direct when-to-use guidance: 'Use this BEFORE cutting — never guess random cut points.' It also names the exact alternative and condition: 'Prefer ae_transcribe_video + ae_transcript_to_cuts when you need to remove stutters/fillers (speech-aware).' This leaves no ambiguity about tool routing.

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