production.material_compare_before_after

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

Annotations declare a non-read-only, non-destructive, non-idempotent mutation; the description adds real value beyond that by stating the default is inspect-only and that even with apply=true, 'Original slots, images, UVs, geometry and animation remain unchanged' — a concrete statement of blast radius. It stops short of explaining permissions/ownership checks or repeat-call behavior.

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 critical default/apply distinction is front-loaded, which is good, but the description opens by restating the tool name and then packs a comma-spliced list of process advice ('lifecycle calls, explicit channels/profiles, technical QA, controlled lighting...') that reads as boilerplate rather than tool-specific information.

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 8-parameter mutating tool with an output schema, the description covers the safety-relevant essentials (default is read-only, apply is scoped to owned candidates, originals preserved). It leaves the identity/lookup parameters and the comparison result semantics unexplained, so an agent could invoke it but may not pick the right params.

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% across 8 parameters, so the description must compensate and only partly does: it explains apply (write gate) and gestures at 'channels/profiles' for the profile/options params. material, material_name, definition, object_name and operation_id are never explained, leaving most of the surface undocumented.

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 the resource (materials) and the compare/apply split: 'inspect or propose by default; apply=true writes only owned candidate materials.' An agent can tell this is a before/after comparison tool that can optionally commit candidate materials. It does not, however, state what the comparison output is or name a sibling it is distinct from (e.g. material_apply_candidate).

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?

'inspect or propose by default' plus the apply=true condition gives a usable when-to-write rule. The rest of the guidance ('Use material plan references for lifecycle calls, explicit channels/profiles, technical QA, controlled lighting and a real visual review before acceptance') is a procedural laundry list without naming any alternative tool or exclusion, so usage is only implied.

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