configure_light_shadows

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

Annotations already establish the safety profile (destructiveHint=true, idempotentHint=true), so the bar is lower, and the description adds meaningful scope detail: values are read back from the light, and the call does not touch whether the light affects the world. It stops short of warning that High/Medium/Low will overwrite any pre-existing custom bias values, which is the destructive consequence the annotation implies.

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-loads the core purpose, then side effects, then returns, with no filler sentences. The Returns field list is long but earns its place because no output schema exists; it is dense rather than wasteful.

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 compensates by enumerating the returned fields, and it covers preset semantics, side effects, and the affect-world boundary. The only gap is the absence of any warning about overwriting existing custom shadow values on the non-binary presets.

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% and the schema already lists the accepted strings, so baseline would be 3; however the description adds genuine meaning by mapping each preset to concrete ShadowBias/ShadowSlopeBias/ShadowSharpen values (0.1/0.1/1.0 etc.) and noting case-insensitivity plus that unknown names are an error.

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?

Names a specific verb and resource (configure shadow settings for a light actor) and immediately constrains scope to preset shadow qualities, enumerating the five accepted values. An agent can distinguish this from sibling light tools like set_light_properties or set_light_intensity 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?

Explains the branching behavior that selects each preset value: Enabled/Disabled only switch cast shadows, while High/Medium/Low additionally write bias/slope/sharpen triples. This is real decision context, though it never names an alternative tool or states when-not-to-use this one versus a general light-property setter.

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