diff_material_instances

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

Annotations already carry readOnly/idempotent/non-destructive, so 'Read-only; nothing is saved' is largely redundant. The description earns credit by adding the 'Editor-only' constraint and, more importantly, by spelling out the full return structure (changed/only_in_a/only_in_b buckets, counts, layer_stack diffs, identical flag), which is real behavioral disclosure beyond the annotations.

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 prose leads with the core purpose and the fork-vs-parent question, so it is front-loaded. The embedded 'Returns' block is long and dense, but since no output schema exists it largely earns its place, keeping this just below full marks.

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 documenting the full return shape, and annotations plus the 'Editor-only'/'read-only' notes cover the operational envelope. An agent has everything needed to invoke it and interpret the result.

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 both parameters are described there as first (baseline) and second (fork). The description mirrors this by calling A the 'parent/original' and B the 'fork', so it reinforces but does not meaningfully extend the schema. Baseline 3 is appropriate.

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+resource ('Diff two Material Instance Constants') and enumerates exactly what is compared (parent, scalar/vector/texture/static-switch overrides, layer stack). This cleanly separates it from the many other diff_* siblings (diff_blueprints, diff_data_tables) by naming the precise asset domain and compared fields.

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 gives the selecting scenario ('Answers "what did this fork change vs its parent (or the original)"'), which tells the agent when this tool is the right one, and flags 'Editor-only' as a constraint. It does not, however, name an explicit alternative or state when NOT to use it (e.g., vs inspect_material_instance_constant), so it stops short of a 5.

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