generate_water_caustics

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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It discloses that the output is 'deterministic' and 'animated,' but does not explain side effects (e.g., whether the input image is modified), the need for an alpha channel or water mask, or the nature of the output file. Important operational details like format, frame counts, and file writing are left to inference.

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 a single, front-loaded sentence with no filler. It states the action, key qualifiers (deterministic, animated, opaque water pixels), and application domains. Every word contributes to understanding, making it highly concise and well-structured.

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 complexity (9 parameters, no output schema, no annotations), the description is incomplete. It does not explain the processing pipeline (e.g., input as a base image), the nature of the caustic effect, how parameters like intensity or delay_ms interact, or what the output format will be. An agent would need more information to invoke it correctly beyond a vague sense of the effect.

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 by explaining parameter roles. It does not define any of the 9 parameters. While names like seed, scale, frames, and intensity are somewhat self-explanatory, the description only mentions determinism and animation without mapping them to parameters or explaining how they alter the effect. It adds minimal value over the raw schema.

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 description clearly states the tool's action and resource: 'Generate deterministic animated light caustics over opaque water pixels.' It also lists specific use cases (oceans, pools, beaches, flooded interiors) which gives concrete context. However, it does not explicitly distinguish it from sibling tools like generate_water_reflection, so it loses the top score for sibling differentiation.

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 gives usage contexts by naming environments (oceans, pools, beaches, flooded interiors) and targets opaque water pixels, implying when this effect is appropriate. But it provides no exclusion criteria, prerequisites, or comparisons to alternatives such as generate_water_reflection or generate_rain_overlay. The guidance is implied rather than explicit.

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