Start a run. Required for every run, including score-only runs (no prompt): generates responses with the prompt when there is one, otherwise copies the graded dataset column and grades it.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It does reveal key behavior (generates responses or copies/grades a column), but it omits details like return value, whether the run blocks or executes asynchronously, and any side effects. This is a meaningful but incomplete disclosure.
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 sentences, front-loaded with the core action ('Start a run'), and every clause adds value. It packs the two usage modes and a key requirement into a concise, well-structured format without redundancy.
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?
Despite its simplicity, the description leaves gaps: no clarification of the id parameter, no return value or execution model, and no guidance on how it relates to sibling tools like runs_create. It explains the core behavior but is not fully complete for a tool with no annotations and no output schema.
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 has 0% description coverage and the description never explains what the required integer 'id' refers to. It is not clear whether this is a run ID, dataset ID, or something else. The description adds no meaning beyond the schema's bare type definition.
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 uses the specific verb 'Start a run' and clearly identifies the resource. It distinguishes this tool from siblings by explaining the two modes: generating responses with a prompt, or copying the graded dataset column and grading it for score-only runs, which makes its purpose unambiguous.
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 by stating it is 'Required for every run, including score-only runs', which tells when to use this tool. However, it does not explicitly name alternatives or exclusions relative to sibling tools like runs_rerun or runs_regrade, so it stops short of 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.
