set_material_properties

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

Annotations already carry readOnlyHint=false, destructiveHint=false, and idempotentHint=true. The description adds genuinely useful behavioral context beyond those flags: partial-update semantics ('Only the provided fields are changed; all fields are optional') and the return behavior ('Returns the updated asset summary'). This is consistent with idempotentHint and clarifies the non-destructive update model. No contradictions found.

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?

Five short sentences, each earning its place: purpose, patch semantics, value formats, return value, and exclusion routing. Front-loaded with the operation, zero fluff, and no repetition of what the schema already states.

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?

For a tool with a ~200-property nested schema and no output schema, the description covers everything an agent needs to invoke it correctly: what it does, partial-update semantics, value/format conventions, the return value, and when to use alternatives. The massive schema carries per-property detail while the description carries the behavioral 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 coverage is 100%, so the schema already documents both top-level parameters and most nested properties with descriptions like 'RGB color [r,g,b] 0-1' and 'Nullable asset reference'. The description adds cross-cutting conventions that apply across the whole properties object: color format, map fields taking asset ids, and patch behavior. This exceeds the baseline 3 by clarifying semantics no single schema entry can express.

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 a specific verb+resource+scope: 'Set any combination of properties on a material asset in one call.' It enumerates representative property families (diffuse, emissive, metalness, gloss/shininess, opacity, maps) and explicitly distinguishes itself from set_material_diffuse and create_assets. An agent can tell exactly what this tool does versus its siblings 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?

Provides an explicit 'When NOT to use' section naming two alternatives with concrete conditions: set_material_diffuse for single diffuse color changes and create_assets type='material' for material creation. This is exactly the routing guidance that prevents wrong tool selection.

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