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

Annotations already declare a non-read-only but non-destructive mutation, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the nudge clamps at the adjacent clip instead of overlapping it, which tells the agent the edit is bounded and cannot create collisions. It does not mention undo, multi-clip grouping behavior, or what is returned.

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?

Two short sentences, front-loaded with the action and its unit, followed by the boundary behavior and a usage cue. There is mild redundancy between "by a few frames" and "For small timing fixes," which restates the same magnitude constraint.

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 four-parameter, non-destructive mutation with annotations and no output schema, the description covers the core mechanic and its clamping rule. It leaves open how multiple clips are treated (individually vs. as a block) and what the caller gets back, which matter for correct invocation on a batch clipIds array.

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 50%: frames carries "+ later, - earlier" and projectId carries a default note, while clipIds and seconds are undocumented. The description partially compensates by establishing that frames and seconds are alternate magnitude units, but it never says whether they are mutually exclusive, whether they combine, or how multiple clipIds are handled.

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 ("Move clips") plus the magnitude and direction of the operation ("earlier/later by a few frames (or seconds)"), which separates it from absolute-position tools like move_clip or content-shifting tools like slip_clip. It never names a sibling explicitly, so the differentiation is inferable rather than stated.

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?

"For small timing fixes" gives an implied scope for when to reach for this tool, and the small-magnitude framing suggests it is not the tool for large repositioning. However, no alternative is named (move_clip, slip_clip, trim_clip all overlap conceptually) and there is no when-not guidance.

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