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

Goes well beyond the annotations: it discloses that omitted fields are filled in with concrete fallbacks (description and image_prompt revert to the title, motion_prompt to a subtle drift, duration to the clip model's default), that the call costs no credits, that it is a single undoable step reversible via undo_storyboard, and that the returned scene number is board-assigned and may not be N+1 on a branched board. None of that is inferable from readOnlyHint/idempotentHint/destructiveHint, and nothing conflicts with them.

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?

Placement rules are front-loaded and every clause carries information — defaults, undo cost, return semantics and credit cost all earn their space. The semicolon-chained sentences make it dense to parse, but there is no filler or repetition.

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 10-parameter mutation with an output schema and no annotation-level safety detail, the description covers the risky parts: fallback defaults, undo scope, credit cost and return-value caveat. Only the cast array and the hold_motion enum are left entirely undocumented, which is a modest gap rather than a blocking one.

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 description coverage is 0% over 10 parameters, so the description has to carry the load, and it does for the hard ones: the three-way semantics of after_scene (omitted / 0 / N), the meaning of continue_from_scene, and the default behavior of description, image_prompt, motion_prompt and duration_seconds. It leaves cast, title, storyboard_id and especially the hold_motion enum values unexplained, so it compensates substantially but not completely.

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?

The first sentence gives a specific verb and resource ('Add one scene to a film') and the whole description keeps the scope tight to scene insertion on a storyboard. That is enough to separate it from siblings like add_storyboard_text, add_captions, update_scene or generate_scene_images without opening a 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?

It states clearly how to position the new scene (append when after_scene is omitted, 0 to put it first, N to splice after Scene N) and that continue_from_scene chains from an existing clip's last frame, which is real when-to-use guidance. It stops short of naming alternatives for the revise-a-scene case (e.g., update_scene) or explaining what to do if the storyboard is locked, so a 4 rather than a 5.

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