preview_images

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

No annotations are provided, so the description carries the full burden. It discloses genuinely useful traits — no inference cost, non-blocking, instant feedback — which tell the agent this is a cheap preview path. It does not describe the return format (thumbnail bytes vs. saved files) or any limits, so the disclosure is partial.

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?

Three short sentences, front-loaded with the core purpose and followed by behavioral and input-format details. 'Fast, non-blocking operation that returns instant visual feedback' is slightly redundant but earns its place by signaling cheapness.

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?

For a tool with no annotations and no output schema, the description covers purpose and input formats but leaves the return shape unresolved — an agent cannot tell whether thumbnails are returned as data, URLs, or written to disk. Adequate but with a clear gap.

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 description coverage is 100%, so the baseline is 3, and the description adds value by enumerating supported input forms (sequences, IFL files, glob patterns) that map to input_path. It does not clarify the input_path/image_paths mutual exclusivity beyond what the schema already states.

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?

States a specific verb and resource ('Generate thumbnail previews for images') and clarifies it happens 'without running inference,' which separates it from run_inference. It does not explicitly name the sibling it competes with (preview_model), but the resource itself is unambiguous.

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 'without running inference' phrasing implies when this tool is preferred over run_inference, and 'Supports sequences, IFL files, and glob patterns' hints at accepted input contexts. However, there is no explicit when-to-use/when-not guidance and no mention of the preview_model siblings.

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