CivitAI Search

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

No annotations are provided, so the description carries the full burden. The description states the HTTP method (GET) and endpoint, which implies a read-only operation. However, it does not disclose whether auth or API keys are required, rate limits, or what happens if the search is empty or the API is unreachable. The enumeration of parameters gives some behavioral hints (e.g., nsfw as a separate filter), but it doesn't describe the return format or pagination behavior beyond the cursor parameter.

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, compact sentence that lists all filters and includes the endpoint. It is front-loaded with the purpose and immediately enumerates the parameters without fluff. It could have been structured as a list, but a single line is efficient. No unnecessary words or repetition.

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 11 parameters, no required ones, and no output schema, the description provides a good overview but lacks depth on edge cases (e.g., default behaviors, error handling, and the meaning of 'cursor' for pagination). The schema covers parameter details, but the description doesn't explain the tool's integration with the rest of the CivitAI ecosystem (e.g., how search results relate to sdnext_civitai_model). It is adequate but not exhaustive.

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 description coverage is 91%, meaning nearly every parameter has a description in the schema. The tool description adds a concise list of all filter names and examples for some (e.g., sort values are given in the schema, not the description). The description does not add new semantics beyond the schema's descriptions, but it does organize them in a single sentence, which is convenient. Since the schema already does the heavy lifting, a baseline 3 is appropriate.

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 searches CivitAI models and explicitly names all filter parameters. It includes the exact API endpoint and conveys the primary action (search) with a specific resource (CivitAI models). While the sibling tools are similar (e.g., sdnext_civitai_model for getting a model by ID, sdnext_civitai_tags for tags), the description's enumeration of filters and the search context distinguishes it sufficiently from the other CivitAI tools.

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 lists all filter categories, implicitly conveying that the tool is the primary search interface for CivitAI. It does not explicitly state when to prefer this over sdnext_civitai_legacy or other CivitAI list tools, but the mention of filters like query, tag, types, and the pagination parameter clearly implies a broad search use case. The absence of explicit exclusions or alternatives is a minor gap but the context is clear.

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