Create and start a fresh copy of a run with the same prompt, dataset, metrics, and settings. Use when the judge changed and you want a clean run instead of mixing versions.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavioral traits. It indicates a mutation (creates a new run) and lists replicated elements, but does not disclose potential side effects, permissions required, or whether the original run is affected. Adequate but lacking detail.
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 only two sentences, front-loaded with the action, and each sentence adds value. There is no redundancy or unnecessary information.
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 simple tool with one parameter and no output schema, the description covers the core functionality and use case. It could clarify whether the new run is automatically started or just created, but overall it is sufficiently complete.
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 0%, so the description must add meaning for the single parameter 'id'. The description implies id is the run to copy, but does not explicitly define it or explain where to obtain it. This adds some meaning but not comprehensive guidance.
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 verb (Create and start), resource (a fresh copy of a run), and scope (same prompt, dataset, metrics, and settings). It distinguishes this tool from siblings like runs_update or runs_regrade by emphasizing a clean copy rather than mixing versions.
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 explicitly tells when to use this tool: 'Use when the judge changed and you want a clean run instead of mixing versions.' It provides clear context but does not name specific alternative tools, leaving some guidance implicit.
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.
