Skip to main content
Glama
multivon-ai

multivon-mcp

Official
by multivon-ai

eval_compare_runs

Compare two report JSONs to calculate pass-rate and score deltas, list regressions and improvements, and provide a McNemar p-value for statistical significance.

Instructions

Compare two multivon-eval report JSONs and return a structured diff.

Loads both reports from disk (the JSON produced by EvalReport.to_json()), pairs cases by case_input, and returns pass-rate / average-score deltas plus the per-case regressions and improvements lists. Includes a McNemar p-value so the agent can tell a real shift from small-sample noise.

Use this when you've made a prompt / retrieval / model change and want to know if the new run actually improved over the baseline — not just on aggregate, but case-by-case.

Args: baseline_json_path: Filesystem path to the baseline report JSON (e.g. "runs/baseline.json"). new_json_path: Filesystem path to the new / proposal report JSON to compare against the baseline.

Returns: A dict with: - pass_rate_delta: float, new - baseline pass rate - avg_score_delta: float, new - baseline average score - regressions: list of dicts with input, baseline_status, proposal_status, baseline_score, proposal_score - improvements: same shape as regressions - mcnemar_p_value: float or null — paired-test p-value - baseline / proposal: summary blocks with name, pass_rate, avg_score, errors, flaky - paired_count / added_count / removed_count: pairing stats so the caller can see how many cases lined up vs. drifted between runs

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
baseline_json_pathYes
new_json_pathYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior4/5

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

Given no annotations, the description discloses key behaviors: reads files from disk, pairs by case_input, computes deltas, and includes McNemar p-value for statistical significance. It is transparent about the operations and return values, though it could mention if the tool has any side effects (likely none).

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

Conciseness5/5

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

The description is well-structured: a one-sentence summary, an explanation of functionality and use case, parameter listing, and detailed return format. Every sentence adds value, and it is concise given the complexity.

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

Completeness5/5

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

With two parameters fully explained and the return format detailed in the description (including nested dicts and lists), the description is complete. It also explains the logic (pairing, McNemar test) and provides context for interpreting results.

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

Parameters5/5

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

The input schema has 0% description coverage, but the description provides an 'Args' section explaining both parameters (baseline_json_path and new_json_path) with examples. This fully compensates for the schema's lack of descriptions.

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?

The description explicitly states it compares two eval report JSONs and returns a structured diff. It uses a specific verb (compare) and resource (multivon-eval report JSONs), and the purpose is distinct from sibling tools that evaluate single aspects.

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?

It clearly specifies when to use (after making a prompt/retrieval/model change to assess improvement) and provides context for case-by-case analysis. However, it does not explicitly mention when not to use or list alternative tools, though the sibling context implies uniqueness.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/multivon-ai/multivon-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server