Destroy a draft MetricVersion (use for either source: 'edit' or source: 'suggestion'). Published versions are refused — to demote a published version, publish a different one as current instead.
| Name | Required | Description | Default |
|---|---|---|---|
| metric_version_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It discloses the destructive nature ('Destroy'), the draft-only restriction, the refusal of published versions, and a workaround. It does not mention irreversibility or error semantics, but 'Destroy' strongly implies permanence.
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, immediately states the core action, and every clause adds value (scope, sources, refusal, alternative). There is no fluff or repetition.
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 destructive tool with no output schema, the description covers the action, constraints, and alternative workflow effectively. It does not cover potential response details or the exact meaning of 'draft,' but these are either implied or domain-specific and not critical for selection and invocation.
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%, and the single parameter has no description. The tool description implies that metric_version_id references the draft version to destroy, and it clarifies which sources are valid. However, it does not explicitly define the parameter's role or format beyond the schema's integer type, so it partially compensates but not fully.
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 action 'Destroy a draft MetricVersion' with specific verb and resource. It also defines the scope (draft only), mentions both source types ('edit' or 'suggestion'), and sets it apart from sibling tools like metric_versions_publish and metric_versions_list by focusing on destruction.
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?
It explicitly states when not to use the tool ('Published versions are refused') and provides a concrete alternative ('publish a different one as current instead'). This gives clear when-to-use and when-not-to-use guidance, with a suggested workflow.
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.
