Metrx MCP Server

Get Experiment Results

metrx_get_experiment_results

Read-onlyIdempotent

Lists an agent's model routing experiments newest first, including status, models, sample counts, traffic split, metric, significance, p-value, and winner; optionally filter by status.

Instructions

List an agent's model routing experiments, newest first: status, control vs treatment model with sample counts, traffic split, primary metric, significance, p-value and winner (control | treatment | inconclusive) where recorded. Optionally filter by status. Do NOT use for starting experiments — use create_model_experiment. Requires an API key with the 'read' scope.

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": {
      "agent_id": "<agent_id>"
    },
    "name": "metrx_get_experiment_results"
  }
}

Input Schema

Name	Required	Description	Default
`status`	No	Only show experiments in this status
`agent_id`	Yes	Agent (UUID) whose experiments to list

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.5.0Nov 10, 2026

changedInput schema / properties / agent_id / description

Previous value: -"Filter experiments by agent"New value: +"Agent (UUID) whose experiments to list"

changedInput schema / properties / status / description

Previous value: -"Filter by experiment status"New value: +"Only show experiments in this status"

changedInput schema / properties / status / enum

Previous value: -[
-  "running",
-  "paused",
-  "completed",
-  "cancelled"
-]New value: +[
+  "draft",
+  "running",
+  "paused",
+  "completed",
+  "cancelled"
+]

addedInput schema / required
```
Added value: +[
+  "agent_id"
+]
```

First observedv0.1.2Mar 8, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds value beyond them by disclosing the sort order ("newest first"), the exact returned fields, the caveat "where recorded" for winner, and the auth requirement ("API key with the 'read' scope"). Pagination or result limits are not mentioned, which keeps it from a 5.

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 payload, the field list, the exclusion and the auth note are packed into three tight sentences with no redundancy. The key routing signal ("Do NOT use for starting experiments") is placed before the low-value auth note rather than buried at the end.

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?

With no output schema, the description carries the burden of describing returns and does so thoroughly, including the winner enumeration and the "where recorded" qualifier for missing data. The one omission is list-size behavior — no mention of limits, truncation or pagination for what is a potentially unbounded listing.

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

Parameters3/5

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

Schema description coverage is 100%, so both parameters — the required agent_id UUID and the status enum — are already fully documented in the schema. The description only restates that status is an optional filter and that results are scoped to one agent, adding no format or semantics beyond the structured fields. Baseline 3 applies.

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?

States a specific verb and resource ("List an agent's model routing experiments") and enumerates the returned fields — status, control vs treatment with sample counts, traffic split, primary metric, significance, p-value, winner. It also names the sibling it is not (create_model_experiment), so an agent can separate it from the mutation tools without opening a schema.

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

Usage Guidelines5/5

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

Gives an explicit exclusion with a redirect: "Do NOT use for starting experiments — use create_model_experiment." It also states the optional filter condition ("Optionally filter by status"), so the agent knows the default behavior is unfiltered listing.

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

Deploy Server