set_look

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

No annotations are provided, so the description carries the full burden of disclosing behavior. It does mention that HDRI is not fetched from the internet (a useful behavioral constraint) and that procedural sky is only visible in certain render engines. However, it does not disclose what happens to existing lighting when this is called, whether it overwrites the whole scene look, whether it requires a Blender session, or what the return/result looks like. For a tool that changes the scene state, this is a significant gap. No contradiction with annotations since none exist.

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 short and front-loaded: the first sentence states purpose and options. The bilingual Korean text adds a bit of redundancy but also adds the procedural-sky/EEVEE note and HDRI constraint. Not much waste, but it could be more structured (e.g., bulleted parameters). Every sentence generally earns its place, but the mixed language and lack of explicit parameter mapping reduce clarity.

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 4 parameters, 0% schema coverage, no annotations, and no output schema, the description is incomplete. It provides some context for sky and hdri but leaves preset and sun_strength unexplained, doesn't describe any return value or confirm what the tool does to the scene state, and doesn't mention whether lighting is applied to the current scene or a new one. This is below the minimum viable for a tool with this much undisclosed context.

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 for all four parameters. It explains sky values ('day, sunset, night, overcast or studio; flat colour, procedural sky, or your own HDRI file') and hdri ('path to your own .hdr/.exr file path'). However, it does not explain preset or sun_strength at all, even though they are key parameters. It also doesn't clarify the relationship between sky='flat' and preset, or between preset and sun_strength. This is only partial compensation for a 0%-coverage 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 states a specific verb and resource: it sets the lighting/sky appearance in a Blender-like scene. It names concrete options (day, sunset, night, overcast, studio; flat colour, procedural sky, or HDRI file) which distinguishes it from sibling tools like camera, set_render, and render_preview. However, it doesn't explicitly name a sibling it is not, so it loses one point for not being fully explicit about differentiation, though the verb 'set' plus resource is clear.

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 provides some guidance: it notes that procedural sky is only visible in EEVEE/Cycles, and that HDRI must be a local path — it won't fetch from the internet. These are conditions for using the parameters, but it doesn't say when to use this tool versus alternatives like set_render or camera. There is no explicit when-to-use or when-not-to-use statement. The added Korean text clarifies constraints but doesn't guide selection among siblings.

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