create_preview_lighting

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

With no annotations, the description carries the full burden. It discloses two key behaviors: 'Safe to re-run: it replaces the previous rig' and 'power scaled to the asset's size.' These go beyond a simple 'creates lights' and give the agent confidence about side effects. It does not detail all possible effects (e.g., optional world settings), but for a creation tool this is adequate.

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?

Two concise paragraphs: the first is a clear one-line summary, the second elaborates on specifics (light names, collection, scaling, re-run safety, usage context). No filler or redundancy; every sentence contributes.

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 (5 params, all documented) and no output schema, the description is fairly complete. It covers what it creates, how it behaves on re-run, and when to use it. It does not mention error conditions or return values, but these are not expected for a creation tool. The optional world settings are described in the schema, so no gap.

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 coverage is 100% – every parameter (objects, replace, strength, world_color, world_strength) has a description. The tool description adds no parameter-specific meaning beyond the schema; the phrase 'power scaled to the asset's size' is not tied to any parameter. Per calibration, baseline 3 is correct when schema does the heavy lifting.

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 opens with 'Build a neutral three-point studio rig sized to the subject' – a specific verb, resource, and qualifiers. It names the exact lights created (AI_Key, AI_Fill, AI_Rim) and the collection (AI_PreviewLighting), which distinguishes it from siblings like create_light (single light) and delete_preview_lighting (removal).

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 explicitly states when to use: 'Use this before render_preview when the scene has no lighting of its own.' That is a clear condition. It does not name alternatives like create_light or set_world_background, but the condition implies when not to use (scene already lit). The re-run safety note is more behavioral than usage guidance.

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