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

Goes well beyond the annotations by disclosing version semantics (repeat calls step further back), retention limits (last 20 saves for 7 days), side effects (re-renders the restored version), cost (no Horizon Units), and the async return path (job_id, then poll job_status, then preview_frame). Nothing here is readable from the structured fields.

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?

Front-loaded with the trigger intent, then parameter sourcing, behavior, exclusions, cost, and return handling in a compact block. Every clause carries information; the quoted user phrases are functional intent anchors rather than filler.

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?

Covers what an agent needs despite an output schema being present: it still names the returned job_id and the follow-up poll (job_status) and verification step (preview_frame), plus limits on how far back undo goes. No meaningful gap for a one-parameter mutation tool.

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 0% for the single required clip_id, so the description has to compensate. It does so by telling the agent where to source the ID ('from list_clips'), which is genuine added meaning, though it does not specify format or edge cases (e.g., a clip with no prior edit).

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 ('undo the last edit' / 'restores the version saved before the last edit') and plainly distinguishes it from edit_clip, delete, and setting-level reversion. An agent can tell exactly what this tool does without opening the 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?

Provides concrete user phrasings that should trigger it ('undo that', 'go back one step') and explicit exclusions with alternatives: deleting a clip is done in RipClip, reverting a single setting means re-calling the edit tool with the old value. When-to-use and when-not-to-use are both covered.

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