Refresh VAEs

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

No annotations are provided, so the description carries the burden. It states the endpoint and resource but doesn't disclose any side effects (e.g., whether it blocks, whether it reloads models, whether it requires specific permissions). For a refresh operation, it is likely a write/update but not destructive, yet no behavioral context is added.

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 a single sentence, direct, and front-loaded with the purpose. It includes the endpoint which is useful, but it's very brief. No waste, but not much substance either.

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?

This is a simple operation with no parameters and no output schema. The description states what it does and the endpoint. For a refresh/rescan tool, it might benefit from mentioning whether it's synchronous, whether it impacts running generations, or whether it reloads models, but given the simplicity, it's adequate. However, it lacks detail on expected behavior after rescan.

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?

There are zero parameters, and the schema coverage is 100% (empty properties). The description mentions 'VAE model folders' but since there are no parameters, the description aligns with the schema. Baseline for zero parameters is 4, but the description is minimal and doesn't add much beyond the endpoint. However, it does clarify the resource type.

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 action ('Rescan VAE model folders') and the endpoint (POST /sdapi/v1/refresh-vae). It distinguishes from sibling refresh tools by specifying the VAE resource, though it doesn't explicitly contrast with sdnext_refresh_checkpoints, sdnext_refresh_unets, or sdnext_refresh_loras.

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 implies usage: call when VAE models have changed on disk to rescan folders. It doesn't provide explicit when-not-to-use or alternatives. Given the sibling refresh tools (checkpoints, unets, loras), it could have clarified that it only refreshes VAE folders, but the resource name is clear enough.

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