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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description goes further by quantifying blast radius per asset_type ('refreshes every keyframe' vs 'one keyframe') and by stating unaffected previews are preserved, which directly bounds the destruction. It omits auth/permission requirements and whether regeneration is synchronous or a long-running job.

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, front-loaded with the action and its approval gate, then the asset-type table in prose, then the exclusion. Every sentence earns its place, though the bare parameter-name phrasing ('A scene_keyframe changes one keyframe') reads slightly clipped.

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, and annotations cover the safety profile. The description supplies the missing blast-radius and approval-gate context, leaving only minor gaps around async completion behavior and 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 description coverage is only 25% across 8 parameters, so the description carries real weight. It usefully interprets asset_type values in terms of downstream effects, but it says nothing about the required idempotencyKey, confirmRegeneration=true (the approval gate it alludes to), or the conditional scene_index/character_id pairing. Partial compensation warrants a baseline 3.

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 (replace/regenerate) plus a clearly bounded resource (an individual storyboard preview), with the per-asset-type behavior spelled out so the agent knows what unit is being replaced. It separates scene_keyframe (one keyframe), character_anchor (dependent keyframes), and style_anchor (all keyframes) crisply. No sibling is named, so it stops short of the 5-level sibling differentiation bar.

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 ('after user approval of the new credit cost') and an explicit exclusion ('Does not regenerate an already finished video shot'), which tells the agent when not to call it. It never names an alternative action (e.g., video_storyboard_revise or video_storyboard_approve), so the routing decision against siblings remains inferential.

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