Skip to main content
Glama

Get a dataset run

getDatasetRun

Fetch a specific dataset run by providing the dataset name and run name, enabling access to evaluation data.

Instructions

Fetch a specific dataset run by name.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
datasetNameYes
runNameYes

Implementation Reference

  • The handler function for the 'getDatasetRun' tool. It takes datasetName and runName, URL-encodes them, and makes a GET request to the Langfuse API at /api/public/datasets/{datasetName}/runs/{runName}.
      async ({ datasetName, runName }) =>
        asJson(await client.get(`/api/public/datasets/${enc(datasetName)}/runs/${enc(runName)}`)),
    );
  • Input schema for 'getDatasetRun' tool: requires datasetName (string, min 1) and runName (string, min 1).
    inputSchema: {
      datasetName: z.string().min(1),
      runName: z.string().min(1),
    },
  • src/tools.ts:255-267 (registration)
    Registers the 'getDatasetRun' tool on the MCP server via server.registerTool() within the registerTools function.
    server.registerTool(
      "getDatasetRun",
      {
        title: "Get a dataset run",
        description: "Fetch a specific dataset run by name.",
        inputSchema: {
          datasetName: z.string().min(1),
          runName: z.string().min(1),
        },
      },
      async ({ datasetName, runName }) =>
        asJson(await client.get(`/api/public/datasets/${enc(datasetName)}/runs/${enc(runName)}`)),
    );
  • src/tools.ts:410-410 (registration)
    The 'getDatasetRun' string is included in the exported TOOL_NAMES constant array for tool name enumeration.
    "getDatasetRun",
Behavior3/5

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

Description implies read-only fetch operation, but does not explicitly state it is non-destructive or require auth; no annotations to supplement, so minimal but adequate.

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?

Single sentence with no filler; front-loaded and efficient.

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

Completeness2/5

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

No output schema, no annotations, and parameters unexplained; description too minimal for a tool with two required parameters.

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

Parameters1/5

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

Parameters have 0% schema description coverage and description does not explain what datasetName or runName represent; must rely on naming alone.

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?

Description clearly states action 'Fetch' and resource 'specific dataset run by name', distinguishing it from listing all runs (listDatasetRuns) or fetching other entities.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus alternatives like listDatasetRuns; lacks context on required inputs or prerequisites beyond schema.

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/hugoles/langfuse-mcp'

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