シーン保存

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

Discloses return value and path semantics. Annotations provide idempotentHint: true, and description adds overwrite behavior. No contradictions.

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?

Two sentences, no wasted words. Front-loaded with action verb and resource. Highly efficient.

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?

Adequately explains purpose, path usage, and return. Does not cover error handling, but annotations and output schema fill gaps. Complete for a simple save tool.

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 coverage is 100%. Description adds example path and explains overwrite behavior when omitted, providing value beyond schema.

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?

Clearly states 'save the current scene' with specific verb and resource. Distinguishes from siblings like dx12_open_scene and dx12_new_scene by focusing on saving.

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?

Provides clear context: path is relative to assets, optional with overwrite behavior. Lacks explicit when-not or alternatives but is sufficient for typical use.

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