production.material_validate_tangent_workflow

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

The description explicitly states 'apply=true writes only owned candidate materials', a mutating behavior, while the annotations declare readOnlyHint=true and destructiveHint=false. This is a direct conflict on the single most safety-relevant trait an agent needs. The useful 'Original slots, images, UVs, geometry and animation remain unchanged' note is negated by the write-mode claim.

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?

Only two sentences and the mode rule is front-loaded, which is good. But the opening repeats the tool name verbatim and the second sentence packs QA process advice ('controlled lighting and a real visual review') that crowds out the parameter and return-value information the agent actually needs.

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 7 undocumented parameters, an output schema present (so returns needn't be explained), and annotations that conflict with the described write behavior, the description is not sufficient to call this tool confidently. It never clarifies whether the default no-op mode does anything observable, nor how the partial-application of profile/definition/object_name is scoped.

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, none required, so the description must compensate and barely does. It explains only 'apply' and vaguely gestures at 'profiles'; it never distinguishes material vs material_name vs object_name vs definition vs options, leaving most parameters unexplained in either place.

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 never states what 'tangent workflow' validation actually checks (tangent-space maps? handedness? sync groups?) or what it returns. It leads with a name restatement and then describes procedural mode behavior ('inspect or propose by default'), leaving the core verb+resource unclear against dozens of sibling validate_* tools.

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; apply=true writes' establishes a mode-selection rule, and 'before acceptance' implies it runs before material_accept. However, no sibling alternatives are named, even though material_validate_normals and game_mesh_validate_tangents are obvious near-neighbors that an agent must disambiguate from.

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