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

Goes well beyond the destructive/non-idempotent annotations: it discloses the cascade side effect of scene-1, that a credit is consumed, the exact REVIEW_CREDIT_REQUIRED return, and the consent condition before retrying with consumeCredit=true. That is exactly the mutation-behavior detail annotations cannot express.

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 tight sentences, each with a distinct job — action, scene-selection consequence, credit path — and the primary action is front-loaded. The parenthetical field list is dense but economical.

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?

No output schema, and the description covers the failure branch plus the credit path, which is the main completeness risk. It does not say what a successful call returns (job id, updated storyboard, or async wait) or whether wait_for_production is then needed.

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?

With only 25% schema coverage, the description carries the load: notes length range and required content style, the meaning of scene selection and its cascading effect, and the purpose/trigger for consumeCredit. Only scenes' enum values come from the schema alone.

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+resource: 'Regenerates the selected scenes with your correction notes'. It is clearly distinct from approve_storyboard or view_storyboard_images, though it never names a sibling to contrast against explicitly.

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 concrete selection guidance (selecting scene-1 regenerates everything for identity continuity) and a clear retry rule for credits. It stops short of saying when to approve instead of requesting changes, which is the obvious adjacent decision.

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