embodied-mcp

Overview Schema Source Related Servers Discussions Admin

convert_dataset

Destructive

Convert embodied-AI datasets between JSONL and LeRobot layouts, preserving numeric features and reporting camera streams without re-encoding.

Instructions

Convert a dataset to another layout: 'jsonl' (canonical, dependency-free) or 'lerobot' (v2.1 parquet, needs pyarrow). Numeric features only; camera streams are reported, not re-encoded.

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": {
      "source": "<source>",
      "destination": "<destination>"
    },
    "name": "convert_dataset"
  }
}

Input Schema

Name	Required	Default
`source`	Yes
`target`	No	jsonl
`episodes`	No
`overwrite`	No
`destination`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 23, 2026

TDQS

B3.4/5.0

Behavior4/5

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

Annotations declare destructiveHint=true and readOnlyHint=false, so the description is not required to carry the safety burden. It still adds real behavioral context beyond the structured fields: lerobot requires pyarrow, only numeric features are converted, and camera streams are reported rather than re-encoded, which tells the agent the output will be lossy for video data.

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

Conciseness4/5

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

Two tight sentences with the layout options front-loaded and zero filler. Slightly cryptic phrasing ('reported, not re-encoded') is the only minor cost.

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

Completeness3/5

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

No output schema exists, and for a destructive mutation tool the description omits key facts: what happens to destination on conflict, what is returned (converted episode count?), and how partial conversion is reported. The format and feature constraints partially cover the gap but leave meaningful omissions.

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

Parameters2/5

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

Schema description coverage is 0% across 5 parameters, so the description must compensate — but it only clarifies the 'target' enum values. It says nothing about source/destination path semantics, the episodes array, or how 'overwrite' (default false) interacts with the destructive behavior.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb+resource ('Convert a dataset to another layout') and names the two supported target layouts with concrete details (jsonl canonical/dependency-free, lerobot v2.1 parquet needs pyarrow). An agent can distinguish this from sibling tools like validate_dataset or summarize_dataset, though it doesn't explicitly contrast with them.

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

Usage Guidelines3/5

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

Usage is only implied by the purpose — convert when you need a different on-disk layout. There is no explicit 'use this when...' guidance, no mention of prerequisites beyond the pyarrow note, and no reference to alternatives among the 18 sibling tools.

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