production.game_mesh_prepare_normals

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

Annotations declare non-read-only, non-destructive, non-idempotent, and the description usefully explains the safety gating: custom normals survive by default and rebuild requires explicit confirmation. That adds real context beyond the annotations, though it doesn't say what the confirmation looks like or what is lost if rebuild is confirmed.

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?

One tightly packed sentence with the key safety constraint front-loaded. No wasted words, though the terseness contributes to the parameter ambiguity noted above.

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 five-parameter tool with no schema documentation and no enums, the description should explain mode values and the confirmation mechanism. The presence of an output schema covers return-value explanation, but the input side remains too thin for an agent to invoke this correctly without guessing.

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?

Five parameters with 0% schema description coverage, and the schema is entirely opaque (mode, options, operation, operation_id, relationship). The description hints at an inspect/propose mode but never maps it to 'mode', and says nothing about operation, operation_id, relationship, or options. It fails to compensate for the coverage gap.

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 names a concrete resource (custom normals) and two modes of action (inspect/propose) on 'a new candidate,' which is clear enough to distinguish it from siblings like game_mesh_validate_tangents or game_mesh_validate. However, 'prepare' is not fully explained — whether it bakes, sets, or just proposes normals is left implicit.

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 partial default policy ('preserve custom normals by default, rebuild only after explicit confirmation'), which tells the agent how the tool behaves but not when to reach for it versus reboot workflows or the validate siblings. No explicit when-to-use or when-not-to-use guidance is stated.

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