Upsert an agreement for (run, response, metric, created_by). Verdict is one of agree, disagree, borderline. corrected_score (1..5) is required when verdict is 'disagree'.
| Name | Required | Description | Default |
|---|---|---|---|
| note | No | ||
| run_id | Yes | ||
| verdict | Yes | ||
| metric_id | Yes | ||
| created_by | No | ||
| response_id | Yes | ||
| corrected_score | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It discloses the write nature via 'upsert' and the conditional corrected_score requirement, but does not cover authorization, idempotency, conflict resolution, or return value behavior. Adequate but not exhaustive.
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 with no redundancy. The first sentence states the action and key, the second clarifies constraints. Every word earns its place.
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 7-param tool with no output schema, the description provides the essential usage conditions and key fields. It omits return value and error behavior, but is otherwise sufficient given the tool's simplicity.
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 coverage is 0%, so the description compensates by naming the key tuple (run, response, metric, created_by) and explicitly defining verdict enum values and the corrected_score condition. This adds semantic value, but the 'note' parameter remains unexplained in both the schema and description.
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 specific verb 'Upsert an agreement' and identifies the unique key tuple (run, response, metric, created_by). This distinguishes it from agreements_list and other resource-specific siblings.
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 usage context is implied through the description of the operation and constraints, but there is no explicit guidance on when to use this tool versus agreements_list or alternative mutation tools. No alternatives or exclusions are mentioned.
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.
