fablecut_silence

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

With no annotations, the description carries the full burden and does so richly: cuts happen last-first in one revision, later material moves up, linked stems stay in sync, locked tracks/clips stay put, and a version is saved before cutting. It also discloses the ffmpeg/ffprobe PATH prerequisite and that inter-clip gaps are untouched.

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?

Front-loaded with the core action and well organized into report behavior, cut behavior, and prerequisites. It is dense and runs long, but nearly every clause carries operational information an agent needs.

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 7-parameter mutation tool with no annotations and no output schema, the description covers safety, ordering, side effects, and prerequisites thoroughly. The one gap is the exact shape of the reported output (spans? per-clip?), which is implied by 'reports every stretch' but not spelled out.

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, but the description adds real meaning on top: threshold is evaluated across all listened stems and must persist for minSilence seconds, padding is quiet kept beside each phrase so words aren't clipped, and tracks defaults to the targeted tracks. It goes beyond restating the schema, though not for every parameter (clipIds linkage is only partly echoed).

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?

Opens with a specific verb+resource pair: find silences in speech, and optionally cut them. The report-vs-cut duality is stated immediately, and it is clearly distinguished from siblings like fablecut_frame (a downstream check) and from the inspector's Silence section, which it mirrors.

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?

Gives explicit workflow guidance: run without cut first to check spans, then cut; lock the music bed before cutting if it should keep running; use force only when the user asked. It stops short of naming a true alternative tool for silence removal, so it is clear context rather than a full when/when-not/alternative set.

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