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

Annotations already declare destructiveHint=true and idempotent=false; the description adds genuinely new context by stating it costs no credits and is reversible via a single undo step with undo_storyboard. It does not clarify whether omitted fields inside 'changes' are preserved or cleared, which matters for a destructiveHint=true mutation.

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 core action, then a compact field list, then two short sentences on undo and cost. The semicolon chain is dense but every clause carries information; minor run-on quality keeps it from a 5.

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 and annotations cover the safety profile, so the description only needs to carry the mutation semantics — which it does, covering scope, field semantics, cost, and reversibility for a 3-parameter nested 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?

With 0% schema description coverage the description carries the burden and mostly succeeds: it maps every field name to plain language, explains 'cast' takes Subject names, and explains that video_model=null inherits the film's model — semantics the schema does not convey. It omits constraints such as the 0.2s duration floor and the hold_motion enum values, and says nothing about partial vs full replacement of the changes object.

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?

Names a specific verb and resource ('Change one scene') and then enumerates every mutable field, including the 1-based scene numbering, so it is clearly distinguishable from add_scene, delete_scene, and update_storyboard. An agent can identify exactly what this tool mutates 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?

Gives useful context on reversibility ('undo_storyboard takes it back') but never routes the agent between this tool and the field-specific siblings set_scene_image, set_scene_clip, or match_scene_motion, which overlap heavily with the image/motion fields here. Usage is implied rather than prescribed.

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