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

With no annotations supplied, the description carries the full burden and does so: it discloses the ripple consequence for later clips, that crossfade overlaps are preserved, that the operation is a single undo step, and the failure precondition ("Fails if there are no gaps"). These are exactly the behaviors an agent cannot infer from the schema and would otherwise learn only by causing a bad edit.

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 core action is front-loaded and every sentence carries information — no filler. It is, however, one dense paragraph with several nested parenthetical asides, which costs a little readability for an agent parsing it in a single pass.

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 mutation tool with six parameters, no annotations, and no output schema, the description covers selection modes, ripple side effects, undo granularity, and the failure case. The omission of expectedVersion (optimistic concurrency) is the only meaningful hole an agent might need to call this correctly.

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 real meaning beyond the 67%-covered schema: itemIds implies a span from earliest to latest (so gaps between them, not just adjacent pairs, are closed), all can be narrowed with trackType, and the mutual exclusivity of the three selectors is stated explicitly — a constraint the schema does not encode (no oneOf). projectId and expectedVersion remain unexplained, which is the only real gap.

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?

"Close the empty gaps between SEVERAL clips at once" names a specific verb (close), resource (gaps between clips) and scope (several at once), then immediately explains the ripple mechanic. It explicitly separates itself from the sibling timeline.close_gap by scoping that tool to the single leading gap.

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 states the selection contract precisely: exactly one of itemIds, trackId, or all:true, and gives a directive for the common ambiguity ("for 'the whole timeline' use all:true, do NOT list ids"). It also routes the excluded case to the correct alternative ("The gap before the earliest selected clip is left alone (use timeline.close_gap for that)").

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