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

With annotations already declaring non-read-only, idempotent and destructive, the description still adds real behavioral context: guide renders start with no credits and are throttled ('a few at a time, the rest wait their turn'), image/video generation is explicitly not started, and retries return the saved result while a changed Film or cut is refused. The one gap is that destructiveHint=true is never unpacked — nothing says what existing clips or bindings are affected or whether the operation can be undone.

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?

Purpose and prerequisites are front-loaded, and the sequence of sentences follows the agent's task order. It is dense but not padded; the main redundancy is the board_prompt/video_prompt sentence, which duplicates the schema's field descriptions.

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 six-parameter nested mutation with an output schema, the description covers the workflow entry point, side effects, cost/throttling, downstream sequencing and retry semantics. The remaining hole is the destructive side effect — what happens to existing scene content — which matters for a tool flagged destructive.

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%, so the description must carry some weight, and it does clarify the drafts contract (consecutive shot uses in edit_ids; board_prompt visual-only versus video_prompt carrying performance, dialogue, sound, continuity and cuts) and that links optionally sets shape links. However, that restates what the nested schema descriptions already say almost verbatim, and parameters like look, after_clip_id and new_scene_title are left entirely to the schema.

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 opening sentence names a specific verb and resource ('Create Film clips from a reviewed 3D cut') plus its ordering and placement semantics ('in cut order, at the chosen place in a scene'). It also implicitly separates itself from prepare_three_d_film_handoff, whose outputs it consumes, so an agent can place it in the workflow without reading the schema.

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 prerequisites precisely ('Copy pin, graph_digest and expected_revision from prepare_three_d_film_handoff') and clarifies a downstream sequencing question agents commonly get wrong ('you can request it right away, because generation waits for each clip's guides'). It stops short of naming competing alternatives such as assemble_film_edit or edit_film_three_d_clip, so the when-not-to-use routing is absent.

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