production.material_validate_normals

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

Annotations declare readOnlyHint=true and destructiveHint=false, but the description states 'apply=true writes only owned candidate materials' – a genuine write path that the annotation denies. That is a direct annotation contradiction. The valuable non-contradictory content ('original slots, images, UVs, geometry and animation remain unchanged') is real, but the mode semantics conflict with the declared safety profile.

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?

Mode information is front-loaded, which is good, but the second sentence is a run-on checklist ('plan references, explicit channels/profiles, technical QA, controlled lighting and a real visual review') that mixes advice, prerequisites and acceptance criteria without structure. Sized reasonably but not tight.

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 described, but with 7 undocumented parameters and a read/write contradiction, an agent still cannot tell what 'profile' or 'definition' should contain or what the validation scope covers. The preservation guarantee is helpful; the parameter contract is not.

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 7 parameters, so the description must carry parameter meaning. It explains only 'apply' (default inspect/propose, true writes to owned candidate materials); 'material', 'material_name', 'object_name', 'profile', 'definition' and the free-form 'options' bag are entirely unexplained, leaving 6 of 7 parameters opaque.

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 name carries the real meaning (validating normals); the text itself only says the tool will 'inspect or propose by default' and write when apply=true. It never states what normal-related checks are performed (orientation, tangent basis, flipped faces, smoothing) nor distinguishes itself from near-identical siblings such as material_validate_tangent_workflow, material_validate_pbr, and game_mesh_prepare_normals. An agent can infer the domain from the name but not the specific operation.

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?

'Use material plan references for lifecycle calls... and a real visual review before acceptance' gives workflow ceremony (create plan references, QA, review) but no when-to-use versus when-not condition and no named alternative validator. It hints this belongs before material_accept, yet never says to run it instead of, or after, material_validate_graph or material_validate_uv.

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