import_file

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

Given that no annotations are provided, the description carries the full burden of behavioral disclosure. It states that format is auto-detected from extension if not specified, which is a useful behavioral detail, but it does not mention any side effects, such as whether the operation overwrites existing objects, triggers a scene reset, or whether it works asynchronously. It also does not describe whether it handles large files or how it internally organizes imported content.

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 concise and front-loaded with the primary purpose and formats. It is two sentences, with no fluff, and the auto-detection note is a valuable addition. Every sentence contributes useful information without redundancy.

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?

The description covers the core purpose and format handling, but it does not explain return values despite having an output schema. The complexity is moderate, and the tool's behavior around format detection is clarified, but the description lacks details on what the tool returns (e.g., object ID, success status) and how it integrates with the scene state, such as whether it selects imported objects. Given the output schema exists, the description doesn't need to detail returns, but it should mention if the imported object is auto-selected or added to a specific collection.

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?

The schema has zero description coverage for parameters, so the description should compensate. It mentions the filepath and format indirectly by saying format is auto-detected if not specified, but it doesn't explicitly describe the format parameter's allowed values beyond supported formats. It does add value by clarifying that format is optional and auto-detected, which is beyond what the schema's 'anyOf' indicates, but it could be more explicit about the parameter semantics.

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 the tool imports a file into the scene and lists supported formats, which effectively distinguishes it from export_file and export_selection among siblings. It names specific actions and resources, though it does not explicitly contrast with load_file, which could be a potential point of confusion.

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?

The description provides context on when to use the tool (importing files) and enumerates supported formats, but it does not explicitly mention when not to use it or suggest alternatives for similar operations. The list of siblings includes load_file and export tools, but the description does not clarify the distinction between import_file and load_file, which might be a gap.

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