Configure fog color, density, opacity, volume type, height range, and falloff in a Marmoset Toolbag scene, creating the fog object when none exists.
Set fog attributes (color, density, opacity, volumeType 'fit'/'vertical', heightMin, heightMax, falloffMin, falloffMax); creates the fog object when the scene has none.
| Name | Required | Description | Default |
|---|---|---|---|
| ref | No | ||
| create | No | ||
| attributes | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and destructiveHint=false, so safety is covered. The description adds genuinely useful behavior — implicit creation when no fog object exists — but leaves open whether supplied attributes merge with or replace existing fog settings, and how this interacts with the separate 'create' parameter (default true).
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?
A single front-loaded sentence with no filler; the verb and resource come first and the creation fallback is attached compactly. The dense parenthetical list is efficient though slightly compressed for an eight-key attribute bag.
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?
An output schema exists, so return values need not be explained, and annotations cover the safety profile. For a mutation tool with a free-form nested object and a 'ref' selector, the description is still missing merge-vs-replace semantics and how 'ref' interacts with the auto-creation behavior.
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 0%, so the description must carry the parameter burden; it does so for the required 'attributes' bag by naming eight accepted keys and the volumeType enum values, which is real value since the schema declares only additionalProperties:true. It does not explain 'ref' (which fog object to target when several exist) or 'create', so compensation is partial rather than complete.
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 (Set) plus the resource (fog) and enumerates the exact attributes it controls, including the accepted volumeType values. The name/description pairing makes it immediately distinguishable from the sibling fog_get without opening either 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?
Usage is only implied: an agent can infer this is the write counterpart to fog_get. The one conditional given ('creates the fog object when the scene has none') describes behavior rather than when to choose this tool over alternatives such as sky_set or object_set_attributes; there are no explicit exclusions or preconditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.