Publish a MetricVersion as the live version of its metric. Works for both 'draft → published' and 'revert to an older published version → current'. Transactionally flips current, demotes peers, and writes the version's instruction + rubric_bands back onto the metric so the judge grades against it.
| Name | Required | Description | Default |
|---|---|---|---|
| metric_version_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it reveals transactional semantics, peer demotion, and writes back to the metric. This goes beyond surface-level; missing only details like permission requirements or failure modes.
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?
Two sentences with no filler: first states purpose, second details side effects. Efficiently front-loaded.
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 one-parameter tool with no annotations or output schema, the description covers core functionality, side effects, and usage context. It could mention return value or error conditions, but the essential behavior is fully explained.
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 single parameter metric_version_id is not explicitly parsed in the description, but the description's explanation of what a version is and how it gets published makes the parameter's role clear. Since schema coverage is 0%, this is a strong compensatory explanation.
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?
Clearly identifies the verb (Publish), the resource (MetricVersion), and the intended effect (make it the live version of its metric). Distinguishes from sibling tools like metric_versions_dismiss and metrics_update by explaining both draft publication and revert flows.
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?
Provides concrete usage context: it works for draft→published and reverting to an older published version, which tells an agent when to invoke it. Does not explicitly exclude alternatives or mention when not to use it, so not a 5.
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.
