resolve_detect_silence

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

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly states the tool is read-only and requires ffmpeg, which are key constraints. It also explains behavior across detect_on modes and the meaning of threshold_db=0 calibration. It does not disclose potential failure modes (e.g., missing ffmpeg) or performance characteristics, but the provided information is substantive and goes beyond schema.

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 two sentences with no wasted words. It front-loads the primary action and constraints, then adds mode explanations and output context. Every sentence earns its 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?

Given the tool's complexity (7 parameters), lack of annotations, low schema description coverage, and no output schema, the description is incomplete. It does not explain all parameters, does not describe the output format beyond scale, and omits potential prerequisites (like ffmpeg version). An agent may need to probe or fail before understanding full 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?

Schema description coverage is 0%, so the description must define parameters. It explains detect_on (carried vs spine) and threshold_db (0 = calibrate per clip), but does not cover tracks, audio_stream, spine_track_type, spine_track_index, or min_silence_seconds. For a 7-parameter tool, this leaves most parameters semantically undefined, requiring agents to guess or inspect the schema (which is also minimal).

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 clearly states the tool's purpose: 'Find dead air on the current timeline' with a specific verb ('Find') and resource ('dead air on timeline'). It also distinguishes itself from siblings by adding 'with ffmpeg (read-only; needs ffmpeg)' and describing modes. No other sibling tool focuses on silence detection, so this tool is unique within the set.

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 explicit context for when to use different detect_on modes ('carried' vs 'spine') and explains calibration with threshold_db=0. It also mentions that return values are timeline-relative, aligning with resolve_get_transcript captions. However, it does not explicitly compare with alternatives like resolve_tighten_silence or state when not to use this tool, leaving some room for inference.

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