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

Far beyond the annotations: it discloses that the scene's video is never generated or charged, that the start frame's charge is not refunded, that this is free, that at least one scene must remain, and that the plan is compacted around the gap. One residual tension is left unexplored – the plan compaction means a repeat call with the same `scene_index` hits a different scene, which sits oddly against idempotentHint=true – but the safety and reversibility profile is otherwise disclosed with unusual precision.

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, and every sentence carries a distinct operational fact (cost, irreversibility, follow-up, minimum-scene constraint). It runs long and leans on caps-heavy emphasis ('REMOVED MEANS REMOVED', 'GONE'), which costs a little crispness but not comprehension.

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 destructive two-parameter mutation with no output schema, the description covers everything an agent needs to call it correctly and then behave correctly afterwards: cost impact, irreversibility, the floor of one remaining scene, and the required re-estimate. Nothing material is left for the agent to guess.

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%, so baseline is 3; the description adds real value beyond it by warning about the off-by-one between the zero-based `scene_index` and user counting ('cut scene 2' means the SECOND frame). It does not restate the `video_id` source, but the schema already does.

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 ('REMOVES one scene from an AI Video Story episode parked at frames review') and pins the exact lifecycle stage. It is cleanly distinguished from the redraw siblings (change_story_scene / regenerate_story_frame) by the explicit 'GONE rather than redrawn' framing.

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 ('the user looked at the frames and wants a scene GONE rather than redrawn'), a timing precondition (before `fire_story_video`), and a required post-action (re-run `fire_story_video` with `estimate_only: true` and announce the new price). The alternative (redraw) is named and ruled out rather than left to inference.

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