シーンを開く

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

Describes side effects: replaces current scene, invalidates old entity IDs, and processes heavy transitions at frame boundaries. Annotations lack readOnlyHint/destructiveHint, so description carries the burden and does so well.

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 concise sentences with no fluff. Front-loads the core purpose, then explains behavior, return value, and side effect. Every sentence adds essential information.

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?

Covers all necessary aspects: what it does (open scene, replace current), path format, heavy transition handling, synchronous return with specific fields, and side effect on entity IDs. No output schema provided, but description compensates clearly.

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?

Only one parameter 'path' with schema description 'assets relative path. Example: scenes/title.json'. Description adds the same context plus an example, going beyond the schema. Schema coverage is 100%, so baseline 3, but added detail justifies 4.

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 clearly states 'Open scene (replace current scene)' and specifies the path is relative to assets. It distinguishes from sibling scene tools (new, save, list) by describing replacement behavior and return value.

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 guidance on when to use: to open an existing scene. Gives caution about old entity IDs being invalid and suggests re-listing. Does not explicitly mention alternatives, but context implies no other tool opens a scene in place.

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