setup_lighting

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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description goes well beyond them by enumerating exactly what is destroyed ('earlier ones are deleted first'), what is preserved ('other lights are not touched'), and the non-obvious side effect that the metal preset also overwrites the world. That is precisely the extra context annotations cannot convey.

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?

Front-loaded with the one-sentence purpose, then scoped by side effects, then presets, then parameters – a sensible order with no filler. It runs long and some lines (the key-light azimuth aside, the metal/world caveat) are dense, but each sentence adds operational information rather than restating structure.

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?

With no output schema, the description still tells the agent where the result surfaces ('The answer has it under `world`') and how to continue (set_world for another HDRI or rotation). Coupled with the destructive scope, preset semantics and target/color guidance, nothing required to invoke this correctly is missing.

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 carries the full load and does so: all five preset enum values are explained with their lighting composition, `strength` is defined as a normal-exposure multiplier, `target` is documented as object names with box-derived size/distance and a default of all visible geometry, and `color` is given as '#rrggbb' or [r,g,b] 0-1.

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?

States a specific verb and resource ('Replace the studio lights with a preset') and immediately scopes it by naming the lights it manages (bl_light_*) versus those it does not touch. An agent can distinguish this from add_light, list_lights and set_world without opening the 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?

Gives clear context: idempotent re-calls are safe, other lights are untouched, and it names set_world as the follow-up for HDRI/rotation/backdrop changes plus a warning that metal needs set_world afterward. It does not explicitly say when to prefer this over add_light for hand-placed lights, so it stops short of full alternatives routing.

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