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

With only readOnlyHint=false from annotations, the description carries the full behavioral load and does so well: caption deletion is reversible soft-delete, scene deletion with "shift" cascades to every lane and shifts later content earlier, a deleted clip leaves its gap open regardless of ripple_secondary, and locked-track cases are refused rather than forced.

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?

One dense paragraph, but front-loaded with the action and then ordered from ripple semantics to gap behavior to refusals, with no filler sentences. Slightly heavy for a single block; the locked-track clause repeats the ripple "none" idea twice.

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 no-output-schema mutation tool this covers what an agent needs before calling: scope, cascade effects, reversibility (captions only), the leftover-gap caveat, and the failure mode with a remedy. The only unstated piece is what the call returns, which matters less than the side effects already described.

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 67% and element_id has no schema description; the description compensates by saying ids refer to a scene, clip, or sticker and by spelling out the ripple_secondary consequences, including naming ripple_delete, which isn't even in the input schema. It adds genuine meaning over the enum's one-line schema text.

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 and enumerated resource set ("Delete a scene, clip, or sticker by id") plus the notable exception that captions are soft-deleted. It does not explicitly distinguish itself from the very similar siblings studio.delete_elements and studio.ripple_delete, so an agent must infer which deletion tool to pick.

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 real decision guidance on ripple_secondary: "shift" (default) ripples everything after, "none" edits the main track alone, and it names ripple_delete as the fix for the leftover gap. It also names the escape hatches for the locked-track refusal (lock_track or ripple_secondary "none"). It stops short of stating when to prefer this tool over delete_elements/ripple_delete.

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