animation_manage

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

The description goes beyond basic operation summaries by disclosing important behavioral details: 'delete' is marked Undoable, 'play' and 'stop' are clearly noted as 'Editor preview. Not saved with scene.', and 'validate' reports 'broken_count + per-track issues' as a return value. It also explains the preset target_path resolution logic and the canonical call shape. With no annotations provided, the description fully carries the transparency burden and does so thoroughly.

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?

The description is long but structured efficiently: a one-line summary followed by a flat list of operations, each with a one-line signature and a brief explanation. It front-loads the purpose and uses consistent formatting. Every sentence adds value—no filler or redundancy. The detailed parameter notes are compact and directly relevant to using the tool.

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?

Given the tool's high complexity (15 operations, many parameters, multiple presets), the description is remarkably complete. It covers every operation's purpose, parameter semantics, return values (for validate, list, get), side effects (undoable, not saved), and call-shape conventions. It also explains edge cases like target_path relative/absolute conversion. The presence of an output schema (not shown) means return values don't need to be fully separately explained, but the description still provides useful output hints.

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?

The input schema only defines an 'op' enum and a generic 'params' object, leaving 0% parameter description coverage. The description compensates entirely by documenting every operation's parameters in detail, including types and examples (e.g., 'keyframes: [{time, value, transition?}, ...]', 'interpolation: linear|nearest|cubic'). It also explains the format for track paths and the high-level tween specs, making the tool fully usable from the description alone.

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 opening line 'AnimationPlayer authoring (player, tracks, autoplay, presets, playback)' clearly states the tool's purpose and scope. The extensive list of ops with specific verbs (create, delete, validate, add_track, set_autoplay, play, stop, list, get, create_simple, presets) leaves no ambiguity about what the tool does. It also implicitly distinguishes from sibling tools like animation_create by focusing on authoring an AnimationPlayer rather than creating animation resources.

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?

Each op is accompanied by a concise description of what it does (e.g., 'Create an AnimationPlayer with empty default library', 'Delete an animation clip... Undoable'), giving clear context for when to use each operation. However, the description does not explicitly contrast this tool with sibling tools (e.g., animation_create) or state when not to use it, so it lacks explicit exclusions and alternative recommendations.

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