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

Annotations only declare the safety profile (write, non-destructive, closed-world); the description adds real behavior beyond that — automatic face detection, face centering at anchorY, the 'never shows edges' clamping guarantee, and per-clip drift. It omits what happens when no face is detected and whether the change is undoable.

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?

It front-loads the intent ('jump-cut punch-ins') then packs the mechanics into a dense single sentence with parentheticals. 'Like a pro edit' and 'like CapCut edits' are flavor rather than instruction, but they anchor intent; the density is high though not wasteful.

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 9-parameter mutating tool with no output schema, the description covers the core mechanics but leaves gaps: no statement of what happens on failure (no faces found), whether it can be undone, or the interaction with existing keyframes/effects. The defaults for base, zoom, and anchorY live in the schema rather than the description, which is acceptable but leaves the overall picture slightly thin.

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 44% across 9 parameters, but the description compensates well: it explains drift's effect with an example value, anchorY's role, detect's trigger condition, clipIds/trackId scoping, and the normal/zoomed alternation that pattern drives. The undocumented schema fields (detect, pattern, clipIds, trackId as types) remain partly unexplained only in their exact semantics.

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 names a specific operation (jump-cut punch-ins) and its target (clips of the main video track or given clips), so an agent can tell this apart from generic effect tools like add_effect or set_keyframes. It does not explicitly name a sibling it should be preferred over, which keeps it short of a 5.

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?

Usage is implied by 'across the clips of the main video track (or given clips)', which tells the agent the default scope, and 'detects faces first if needed' implies ordering. There is no explicit when-not guidance or named alternative (e.g. add_keyframe/set_keyframes for manual punch-ins), so the agent has to infer the choice.

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