water

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

With no annotations provided, the description carries the full behavioral burden, and it does so fairly well. It discloses that water fails silently when size is below the simulation grid and reports an error, that drift can be used to verify water movement, and that empty obstacles means all visible meshes except the floor plate are used.

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 well organized: a one-sentence summary, then a compact parameter reference with each item on its own line. The English/Korean duplication adds mild redundancy, but the density of useful information justifies the length for a 23-parameter 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?

The tool is complex with 23 parameters, no annotations, and no output schema, so the description needs to be quite thorough. It covers core behavior well and even mentions drift as a result signal, but it omits seven schema parameters and gives no workflow guidance about frame ranges or domain setup, leaving the agent under-informed for advanced calls.

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%, so the description must compensate, and it documents 16 of 23 parameters with concrete units, ranges, and defaults. However, several parameters like frames, domain_at, domain_size, smoothing, start_frame, preview_frames, and particle_radius are not described, leaving meaningful gaps for an agent.

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 clearly states a specific action and resource: creating liquid water in forms such as drops, streams, pools, or object-converted meshes. This distinguishes it from sibling tools like fire, smoke, and ocean, which cover different physical effects.

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?

The description explains the tool's own modes and parameters but never contrasts it with alternatives like splash, ocean, or particles. There is no guidance on when to choose water over a sibling tool, so the agent must infer usage from the name and context alone.

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