Skip to main content
Glama
Sign In
deepset-ai

deepset-mcp

Official
by deepset-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

list_experiments

List workspace Experiments, newest first, optionally filtered by pipeline, to compare candidate pipeline versions against baselines on dataset test cases and review statuses and results.

Instructions

Lists the workspace's Experiments, newest first.

An Experiment compares a candidate pipeline version against a baseline on the test cases of one Dataset: each side gets its Sessions (reused, or replayed against its version) and is scored by the same Metric Group. The baseline is another version, or, when recorded, the Sessions the Dataset recorded. status and each side's status go REPLAYING, SCORING, then ENDED or FAILED; a side's error says why it failed and scoring_counts how its evaluations ended. Read how the candidate did against the baseline with get_experiment_results. To read one side's scoring run cell by cell, pass its scoring_runs[].experiment_run_id, that entry's pipeline_id resolved to a name with list_pipelines, and the Experiment's metric_group_id to get_experiment_run. :param pipeline_name: Only Experiments with either side on this pipeline, when given. :returns: The Experiments, or an error message.

The output is automatically stored and can be referenced in other functions. Returns a formatted preview with an object ID (e.g., @obj_123). Use the object store tools in combination with the object ID to view nested properties of the object. Use the returned object ID to pass this result to other functions.

Input Schema

NameRequiredDescriptionDefault
pipeline_nameNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.1.31
    • addedInput schema / properties / pipeline_name / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedInput schema / properties / pipeline_name / default
      Added value: +null
    • removedInput schema / properties / pipeline_name / type
      Removed value: -"string"
    • removedInput schema / required
      Removed value: -[
-  "pipeline_name"
-]
  2. Addedv0.1.29

TDQS

A4.2/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden, and it does substantial work: it discloses the status lifecycle (REPLAYING -> SCORING -> ENDED/FAILED per side), the semantics of the side's error and scoring_counts fields, and that output is auto-stored with an @obj_NNN preview. Gaps remain: no mention of pagination, result limits, or permissions for a list tool.

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

Conciseness3/5

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

The purpose and filtering/routing content is front-loaded and useful, but the trailing object-store block repeats itself across four sentences ('The output is automatically stored...', 'Returns a formatted preview...', 'Use the object store tools...', 'Use the returned object ID...') and could be compressed to one. The domain paragraph is dense but earns its place.

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 and no annotations, the description must cover returns and behavior; it states ':returns: The Experiments, or an error message' and explains the @obj_NNN preview mechanism. Combined with the status/error/scoring_counts lifecycle detail, an agent has enough to call and interpret it, though pagination/limits are unaddressed.

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?

Schema coverage is 0% and the single parameter has no schema description, but the description compensates explicitly: 'pipeline_name: Only Experiments with either side on this pipeline, when given.' That clarifies both the matching semantics (either side) and the optional nature, adding real meaning beyond the bare anyOf string.

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 with scope: 'Lists the workspace's Experiments, newest first.' It then defines what an Experiment is and names the siblings it is not (get_experiment_results, get_experiment_run), so an agent can distinguish it from other experiment 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 Guidelines4/5

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

Explicitly routes the agent: use get_experiment_results to compare candidate vs baseline, and get_experiment_run with scoring_runs[].experiment_run_id plus list_pipelines for cell-level reading. It also explains when the pipeline_name filter applies ('when given'). It lacks an explicit when-not-this-tool statement, but context is clear.

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

Deploy Server

Other Tools