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

Annotations already declare destructiveHint=true and idempotentHint=true, so safety and retry semantics are covered structurally. The description adds the critical side effect that this spends existing credits and clarifies the output is previews rather than finished video, which is real behavioral context beyond the annotations.

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?

Three short sentences, no filler, and the trigger condition and cost warning are front-loaded and easy to scan.

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?

An output schema exists, so return values need no explanation. The description covers the preconditions, cost, and output nature; the only notable gap is guidance on the idempotencyKey for safe retries on this destructive, costly operation.

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 description coverage is only 20%, so the schema does not carry the burden. The description usefully explains the confirmApproved gate (must be true to start production), but says nothing about workspaceId, projectId, revisionId, or the idempotencyKey's role despite idempotentHint being set.

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 (approve/start production) plus the concrete resources it produces: reference images and scene keyframes. It also disambiguates against video-generation siblings by stating this stage 'produces reviewable previews, not animated videos.' An agent can distinguish it from video_storyboard_create and video_assets_approve without opening schemas.

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 a clear precondition: use it after the storyboard and its credit estimate have been shown, with confirmApproved=true. It does not name an explicit alternative tool or state exclusions, but the gating condition is unambiguous.

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