Caption Image (OpenCLIP)

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It does add useful context about mode variants and the analyze breakdown, but it does not disclose side effects, response format, or whether the operation is purely read-only.

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 two well-structured sentences, front-loaded with the core purpose and endpoint, followed by key parameter behavior. Every sentence earns its place without redundant filler.

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?

With 12 parameters, 50% schema coverage, and no output schema, the description is too thin to be considered complete. It covers the core purpose, modes, and analyze flag, but omits return-value expectations and the numerous tuning parameters, leaving the agent with significant ambiguity for a non-trivial tool.

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 coverage is 50%, and the description adds some meaning to `mode` and `analyze` by listing mode values and the specific breakdown categories. However, many parameters like `num_beams`, `max_length`, `flavor_count`, and `clip_model` are left unexplained, so the description only partially compensates for the schema 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 clearly states the tool generates a text caption/prompt from an image using OpenCLIP+BLIP and identifies the endpoint. It is specific and unambiguous, but it does not explicitly distinguish this tool from nearby siblings like sdnext_tagger, sdnext_vqa, or sdnext_caption_dispatch.

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 offers mode and analyze guidance, but no guidance on when to choose this tool over alternatives such as tagger, vqa, or analyze. There are no exclusions, prerequisites, or sibling comparisons.

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