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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely useful non-schema behavior: no token spend, nothing created, an empty placeholder for queued/processing jobs, duplicate-card risk, and a terminal fallback to the returned `url`. It does not describe the result shape, but with the idempotency and read-only hints already present, this sits at an adequate rather than exceptional level.

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 action and the WHEN clause before the caveats, and every sentence carries either a routing rule or a behavioral constraint. It runs long and stacks several prohibitions in one dense paragraph, which slightly hurts scannability.

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?

Full coverage for a 2-param read tool with no output schema: the agent is told when to call, when not to, what appears on screen, what to write alongside it, and what to do if no card renders. Nothing needed to invoke it correctly is absent.

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 100% and the `media` enum's mapping (which transforms count as `video`, story episodes are `video`) is already spelled out in the schema description, so the description largely restates it. The one added nuance is the frame-review episode case, which is marginal beyond the schema.

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 and resource ("Shows an EARLIER aicut generation to the user again, in the aicut card"), and immediately enumerates the rendered payload (video/image/audio plus cost and timestamp). It is clearly distinguishable from `get_video`/`list_videos`, which retrieve data rather than re-display a card.

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 an explicit WHEN clause, an explicit prohibition (never call after a `generate_*`, never per wait, never twice per turn), and a named exception for the story-frame-review case. The alternatives for finding ids (`list_videos` / `list_images` / `list_audio`) are named so the agent knows the routing precondition.

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