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

Goes far beyond the annotations: it discloses the audio-safe edge algorithm (~80 ms quietest point, 0.25 s word lead-in/release, never past the word), what snap_to_words:true vs false does, the camera-cut flash avoidance (edges up to 6 frames past a cut are pushed back), and that the result reports every move and any speech-joining cut. With destructiveHint/idempotentHint already declared, this is pure added value.

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 content earns its place, but it is delivered as one dense 150-word paragraph with nested parentheticals and repeated phrasing ('lands audio-safe' twice, 'cut edge' restated), so an agent must parse a lot before reaching the snap_to_words and camera-cut rules. Front-loading is good, structure is not.

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 wholesale editorial rewrite with no output schema and only partial annotation coverage, the description covers scope, when-to-use, edge behavior, snapping and result reporting. The one gap is reversibility — nothing says whether the prior keep list can be undone (reset_edit/restore_range exist as siblings) or what happens to prior edits.

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 only 33%, so the description must carry the load, and it largely does: it defines segments as the keep list of [start,end] pairs and gives both branches of snap_to_words. The time basis (source frames vs seconds) of the segment values is still implicit, which keeps it short of a 5.

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?

States a specific verb and resource ('REPLACE the keep list') plus the exact input shape 'SOURCE [[start,end],...]' and the scope consequence ('Everything else is cut'). It explicitly distinguishes itself from the sibling tools that handle the same domain by naming cut_range and restore_range.

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 an explicit when-to-use ('only for wholesale restructuring, always after get_edl'), an explicit when-not/alternative ('for local fixes prefer cut_range/restore_range'), and the scoping rule (acts only on the explicit project_id, never the active-project pointer). Nothing is left to inference.

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