Import a promptfooconfig.yaml. Creates a prompt, a dataset from the test vars, and metrics from the assert blocks (llm-rubric/g-eval become judge metrics; contains/equals/regex/is-json become deterministic check metrics). Returns a summary of what mapped and what was skipped and why; nothing is dropped silently.
| Name | Required | Description | Default |
|---|---|---|---|
| config | Yes | The full promptfooconfig.yaml contents. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses the mapping rules (llm-rubric/g-eval to judge metrics, deterministic asserts to check metrics), the return of a summary, and the guarantee that 'nothing is dropped silently.' This is substantial behavioral disclosure, though it could add details on error handling or idempotency.
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 three sentences, front-loaded with the core action, and each sentence adds essential information: what it does, how it maps, and what it returns. No wasted words or redundant phrases.
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?
The description covers the input (yaml contents), the mapping logic, and the output (summary of mapped/skipped). It also states the non-silent-drop policy. Given the simplicity of the input schema and no output schema, this is nearly complete. It could mention error behavior for malformed YAML, but that is not critical for understanding the tool's purpose.
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 already provides 100% coverage for the single 'config' parameter, describing it as 'The full promptfooconfig.yaml contents.' The description reinforces this by mentioning the filename format, but does not add deeper parameter semantics beyond the schema. 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's function: 'Import a promptfooconfig.yaml' and explicitly describes the resulting artifacts (prompt, dataset, metrics). This distinguishes it from sibling tools that individually create prompts, datasets, or metrics, making the purpose unambiguous and specific.
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 provides clear context: this tool is used when you have a promptfooconfig.yaml to import, and it explains what will be created. However, it does not explicitly mention alternatives or when not to use this tool, so it does not fully meet the 'explicit when/when-not' criteria. The implied usage is strong enough to warrant a 4.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource and action, with clear separation across agreements, datasets, judges, metrics, prompts, runs, tags, and usage. Even similar tools like datasets_create vs datasets_create_from_url and runs_generate vs runs_rerun are explicitly differentiated in their descriptions.
The overwhelming majority of tools follow a consistent plural_resource_action snake_case pattern (e.g., datasets_create, metrics_update, runs_retry_failures). The only slight deviation is promptfoo_import, but it is still descriptive and does not break the overall predictability.
With 54 tools, the server far exceeds the 25+ threshold considered too many, and approaches the 50+ extreme mismatch level. Even for a broad LLM evaluation platform, this count is excessive and likely to overwhelm agents, making tool selection more error-prone.
The toolset provides full CRUD for core resources (datasets, metrics, prompts, runs, tags) plus lifecycle operations like publish, generate, regrade, and retry. It also includes cross-cutting utilities (usage, import, provider credentials). Minor gaps exist, such as no update/delete for agreements and no cross-run response search, but these are non-essential for the primary workflows.
