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

Annotations already mark this as destructive, non-idempotent, and read-only=false, so the bar for additional value is higher. The description still adds substantial context: 9 credits charged only on success, 1.5–6 minute asynchronous duration with a stillDrawing return path, retention of dialogue/captions, refusal during active runs, and the need to reassemble afterward. This fully enriches the annotation profile without contradicting it.

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?

Every sentence carries actionable information: cost, substitution behavior, retention policy, timing, failure mode, concurrency restriction, and post-condition. The core operation is front-loaded, and there is no redundant restatement of the schema or title.

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?

This is a high-complexity tool with no output schema, yet the description covers the essential behavioral surface: asynchronous completion, credit charging, content-filter handling, concurrency constraints, cross-tool dependency on status, and follow-up assembly. An agent has what it needs to call the tool correctly and interpret the stillDrawing outcome.

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%, with prompt and panelId already documented, but the description adds meaning beyond the schema: prompt is explicitly tied to replacing the scene description and to the content-filter rewording strategy, and panelId is tied to failedPanels from aetherwave_comic_status. projectId lacks a schema description, but the tool-level context makes its role clear enough.

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 description opens with a specific verb and resource: 'Redraws a single panel, replacing its current image.' It clearly distinguishes this from the sibling aetherwave_comic_draw by anchoring on a single panel and contrasting with a 'full drawing run,' so an agent can tell them apart without opening either 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?

The description gives concrete when-to-use guidance: use it for single-panel redraws, avoid it while a full drawing run is active, and re-run aetherwave_comic_assemble if the page was already assembled. It also advises rewording the prompt rather than retrying when a content-filter refusal is encountered, which is explicit operational guidance beyond what the schema provides.

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