@argosvix/mcp-server

compare_eval_runs

Compare two eval runs to detect regression or improvement by analyzing per-criterion score deltas and failed count changes.

Instructions

Compare two eval runs (baseline / candidate) and return per-criterion mean score deltas + the failed count delta + a verdict (GET /v1/eval-runs/compare). Lets an AI agent grasp "how did the candidate change relative to the baseline" in one call, for prompt-improvement measurement and regression detection. verdict = improved / regressed / mixed / unchanged. The failed count treats scores <= 2 as "failed". Same account only.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "baselineRunId": "<baselineRunId>",
      "candidateRunId": "<candidateRunId>"
    },
    "name": "compare_eval_runs"
  }
}

Input Schema

Name	Required	Description	Default
`baselineRunId`	Yes	Id of the baseline run (list_eval_runs.runs[].id)
`candidateRunId`	Yes	Id of the candidate run (same source); must differ from the baseline

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.30.0-alpha.14Jul 8, 2026

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses return format (deltas, verdict), verdict options, failed count definition (scores <= 2), and account constraint. With no annotations, this covers key behavioral traits adequately.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single paragraph with clear progression: action, value, details. Efficient but could be slightly more concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Explains key outputs (deltas, verdict) and failed count rule. No output schema, so description carries load. Adequately complete for a comparison tool, though could mention edge cases like identical runs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Adds context beyond schema: baselineRunId references list_eval_runs.runs[].id, candidateRunId must be from same source and different from baseline. Schema coverage is 100%, so description adds meaningful usage guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it compares two eval runs, returning per-criterion mean score deltas, failed count delta, and a verdict. Distinguishes from siblings like list_eval_runs and get_eval_run by focusing on comparison.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Describes use for measuring prompt improvement and regression detection. Implicitly contrasts with single-run access tools, but does not explicitly exclude cases where alternative tools are more appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server