Suggest an improved version of a prompt, grounded in a run's test results and judge feedback. Analyzes the run's responses, scores, and reviews, then returns reasoning plus a rewritten template (preserving {{variables}}) and persists it as a Suggestion. Requires a run that has a prompt (not a scoring-only run).
| Name | Required | Description | Default |
|---|---|---|---|
| run_id | Yes | The run whose results ground the improvement. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses important behaviors: it analyzes run data, returns reasoning and rewritten template, preserves {{variables}}, and persists a Suggestion. This gives a clear picture of the tool's operation and side effects, though it does not cover all edge cases.
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 purpose, and every sentence adds meaningful detail without redundancy. It is efficient and well-structured.
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 what the tool does, how it does it, what it returns (reasoning + rewritten template), and a key prerequisite. Given the simplicity (one parameter, no output schema), it is thorough and 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?
The single parameter run_id is well-described in the schema (100% coverage), and the description adds crucial context that the run must have a prompt, enriching the parameter semantics beyond the schema.
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: suggesting an improved prompt based on run results and judge feedback. It specifies the resource (prompt), the action (improve/suggest), and differentiates it from simpler prompt tools by emphasizing grounding in test results and persistence as a Suggestion.
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 a clear use case (improve prompt using run feedback) and a prerequisite (run must have a prompt). However, it does not explicitly mention alternatives or when not to use this tool, so it falls 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.
