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

Adds real behavioral context beyond annotations: card/line/duration limits (30-second cards, six lines, five minutes), optimistic-concurrency framing via the current revision, and explicitly that there is no Brix36 planning model, media generation or credit charge. The retry sentence partly restates idempotentHint=true but adds the "returns the saved result" semantics. No permission/auth disclosure, which is the main remaining gap.

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?

Four compact sentences, front-loaded with the core action before constraints and cost notes. Dense but nearly every clause carries a distinct fact; only the retry sentence overlaps with the idempotency annotation.

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?

Output schema exists, so return values need no explanation, and the description covers the important operational constraints (limits, concurrency, no credit charge) for a complex nested write tool. It is only incomplete in that it never positions itself against sibling write tools or notes permission requirements.

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 a moderate 71% and the schema already documents most parameters in detail (scenes shape, castIds ordering, language, expectedRevisionId, operationId). The description contributes only the "visualWorld is required for quoting" constraint; it doesn't explain expectedRevisionId null semantics or the scenes array structure. Baseline 3 fits.

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?

Specific verb ("Saves") plus a concrete resource list (Film scenes, visualWorld, camera directions, dialogue) tied to a scope ("against the current revision"). An agent knows exactly what the call persists, though it never distinguishes itself from close siblings like studio_film_script_write or studio_sections_update.

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?

Implies usage through qualifiers — "finished" scenes, work against "the current revision," and the note that visualWorld is required for quoting — but never states when to choose this over studio_film_script_write or studio_sections_update, nor any prerequisites such as auth or project state.

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