production.texture_dependency_report

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

The description explicitly states that apply=true writes materials, while annotations declare readOnlyHint=true. This directly contradicts the structured safety metadata, even though the description also usefully says original slots, images, UVs, geometry, and animation remain unchanged.

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 description is only two sentences and front-loads the apply/default behavior, but the second sentence is dense with general process jargon and does not add proportionate value.

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 seven-parameter tool with zero schema coverage and a write path, the definition is under-specified. The output schema may cover return values, but parameter meanings and the read/write contradiction leave an agent without enough reliable context to invoke this safely.

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 seven parameters. The description explains apply=true and hints at profile/channel use, but options, definition, material, material_name, and object_name remain completely unexplained.

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 indicates a report/inspection tool that can optionally write candidate materials, but it never states what a 'texture dependency report' actually contains or how it differs from texture_inspect or material_analyze_texture_sets. The purpose is inferable but vague.

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?

It gives a default ('inspect or propose by default') and general prerequisites involving material plans, channels/profiles, QA, lighting, and visual review, but it does not name when to use this tool versus sibling tools like texture_inspect or material_validate_*.

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