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

Annotations already declare non-read-only, non-destructive, non-idempotent behavior, so the description's added value is the state prerequisite (only failed videos) and the reason for the audio restriction (HypeFox deletes the audio on completion or failure). It does not say whether a retry replaces the failed video or creates a new one, nor whether credits are consumed, which are the remaining behavioral gaps for a regeneration tool.

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?

Two tight sentences: the action and preserved context come first, then the exception and its alternative. No filler, and the most important routing constraint is front-loaded enough to be actionable.

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?

For a one-parameter, no-output-schema tool with annotations covering the safety profile, the description supplies what is needed to call it correctly: the failure precondition and the audio exclusion with an alternative. Only the retry's effect on the original video and any cost implication are left unstated.

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?

The single parameter has 0% schema description coverage, but its identity is obvious from the tool's framing. The description does add implicit meaning — the video_id must reference a failed video and must not be audio-based — though it never names the parameter or states that constraint in terms of it.

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?

States a specific verb and resource ('Makes a failed video again') plus the scope of what is preserved (idea, facts, style, voice). It is clearly distinguishable from make_video (new video) and make_video_from_audio (audio-sourced case), which the description explicitly names.

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 the positive condition (the video failed and 'didn't count') and the negative condition with the exact alternative: audio-based videos cannot be retried, use make_video_from_audio instead. Both when-to-use and when-not-to-use are explicit.

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