export.file

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

Beyond the annotations (destructive, non-idempotent), the description discloses the gated risk, the local-user approval requirement, the prohibition on self-approval, the retry-with-same-request-id flow, and the committed-snapshot prerequisite. This is rich behavioral context that materially changes how an agent should handle the tool.

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 compact and front-loaded, stating the command and risk level first, then packing approval behavior and prerequisites into two efficient sentences. There is no filler; every clause contributes operational information an agent needs.

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?

It covers approval and prerequisite context well, and the output schema plus annotations help cover return-value and safety concerns. However, the export parameters are extension-dependent and the schema lacks descriptions for path and most options, leaving the agent without enough detail to reliably construct valid parameters.

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 description adds meaning to some parameters: path must be an approved output root, snapshotId must reference a committed snapshot, and _requestId is reused after user approval. However, schema description coverage is only 44%, and many parameters such as overwrite, frameStart, frameEnd, and _transactionId remain unexplained in both the schema and description, so it only partially compensates 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 states the command as 'export.file', which conveys a specific verb (export) and resource (file), and the harness context clarifies it is the Blender file-export operation. It does not explicitly differentiate it from the sibling blender_export_extended, so it falls short of a 5.

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 clearly states key invocation conditions: local user approval is required, the same request id must be retried after approval, an approved output root is required, and a committed snapshot must exist. It does not compare against alternatives like blender_export_extended or state when this tool should be avoided, so usage guidance is contextual but not fully directional.

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