> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring.md).

# Evaluations and monitoring

Choose a tool by the result you need. Read tools inspect resources. Change tools save or publish data. Run tools execute a workflow or evaluator.

A **dataset** contains test cases. An **evaluator** scores an output. An **experiment** applies a project version to a fixed set of cases. A **monitor** scores a sample of future live runs.

## Datasets

| Tool                                                                                                                                  | Effect | Use it to                                                                            |
| ------------------------------------------------------------------------------------------------------------------------------------- | ------ | ------------------------------------------------------------------------------------ |
| [evals\_datasets\_list](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-datasets-list.md)        | Read   | Find evaluation datasets for a project, optionally filtering by name or search text. |
| [evals\_datasets\_get](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-datasets-get.md)          | Read   | Read a dataset and, optionally, a page of its test cases.                            |
| [evals\_datasets\_create](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-datasets-create.md)    | Change | Create a collection of test cases for evaluating a project.                          |
| [evals\_dataset\_rows\_add](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-dataset-rows-add.md) | Change | Add test cases to an existing dataset.                                               |

## Evaluators

| Tool                                                                                                                                                  | Effect | Use it to                                                                      |
| ----------------------------------------------------------------------------------------------------------------------------------------------------- | ------ | ------------------------------------------------------------------------------ |
| [evals\_evaluators\_list](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-evaluators-list.md)                    | Read   | Find evaluators for a project.                                                 |
| [evals\_evaluators\_get](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-evaluators-get.md)                      | Read   | Read an evaluator’s scoring rules and required input/output structure.         |
| [evals\_evaluators\_create](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-evaluators-create.md)                | Change | Create an evaluator that scores outputs using a built-in rule or an LLM judge. |
| [evals\_evaluators\_preview](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-evaluators-preview.md)              | Run    | Dry-run an evaluator configuration on 1 to 3 samples before saving it.         |
| [evals\_evaluator\_templates\_list](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-evaluator-templates-list.md) | Read   | Discover evaluator templates before configuring a new evaluator.               |

## Experiments

| Tool                                                                                                                                     | Effect | Use it to                                                                                                                                                                                      |
| ---------------------------------------------------------------------------------------------------------------------------------------- | ------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [evals\_experiments\_list](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-experiments-list.md)     | Read   | Find experiments for a project.                                                                                                                                                                |
| [evals\_experiments\_get](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-experiments-get.md)       | Read   | Read an experiment’s configuration, summary results and, optionally, a page of individual results.                                                                                             |
| [evals\_experiments\_create](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-experiments-create.md) | Change | Freeze dataset rows into an experiment using a project version.                                                                                                                                |
| [evals\_experiments\_run](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-experiments-run.md)       | Run    | Generate outputs or score existing outputs with explicit evaluator IDs.                                                                                                                        |
| [evals\_experiments\_status](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-experiments-status.md) | Read   | Poll one accepted job with its experiment\_id and job\_id from evals\_experiments\_run, or omit job\_id to inspect the experiment's latest job with cumulative row counts and aggregate cards. |

## Monitors and run scores

| Tool                                                                                                                                    | Effect | Use it to                                                              |
| --------------------------------------------------------------------------------------------------------------------------------------- | ------ | ---------------------------------------------------------------------- |
| [evals\_monitors\_list](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-monitors-list.md)          | Read   | Find quality monitors for a project.                                   |
| [evals\_monitors\_get](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-monitors-get.md)            | Read   | Read a monitor with optional score statistics and alert configuration. |
| [evals\_monitors\_create](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-monitors-create.md)      | Change | Create a monitor that samples future project runs for one evaluator.   |
| [evals\_run\_scores\_list](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-run-scores-list.md)     | Read   | Review a run’s score history, including repeated evaluations.          |
| [evals\_run\_scores\_create](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-run-scores-create.md) | Run    | Append one evaluator score for an existing project run.                |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
