draftkingsapi-mcp

Sample rows (keyless)

get_demo_sample

Read-only

Returns frozen sample rows that show a dataset's response shape for schema inspection; do not present them as real data. No key or credits required.

Instructions

Frozen sample rows that show a dataset's response shape. Never present them as data. No key needed, no credits.

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": {
      "dataset": "<dataset>"
    },
    "name": "get_demo_sample"
  }
}

Input Schema

Name	Required	Description
`task`	No	Optional: the user's task in one plain sentence, nothing personal. Helps the API return what fits.
`limit`	No	Rows to return, at most 100.
`sport`	No	Sport code in upper case, for example NFL, NBA, NHL, MLB, NCAAF, NCAAB, SOCCER.
`dataset`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 15, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Beyond readOnlyHint=true and openWorldHint=true, the description adds real behavioral facts: the rows are frozen/static, require no API key, and consume no credits. That is meaningful context an agent could not derive from annotations. It does not say how many rows are typical or whether the shape varies by dataset.

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?

Three short sentences, front-loaded with what the tool returns, followed by the critical warning and the cost/auth note. Every sentence carries distinct information with no filler.

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?

For a read-only sampling tool with no output schema, the description conveys what comes back (sample rows revealing response shape) and that results are non-authoritative. The main remaining gap is not mapping the dataset enum to the corresponding real-data sibling tools, which would complete the workflow picture.

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 75% with 4 parameters, so the schema already documents task, limit, sport, and the dataset enum. The description only alludes to 'a dataset's response shape,' adding a sliver of meaning to the dataset param but nothing about limit, sport, or task.

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: 'Frozen sample rows that show a dataset's response shape.' This is clearly not a data query, which implicitly separates it from siblings like get_odds or get_stats_games, though none are named explicitly.

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?

It gives a usage constraint ('Never present them as data') and a cost signal ('No key needed, no credits'), but never says when to prefer this over the real data siblings or what workflow it fits (e.g., inspect shape before a full query). Usage is implied rather than stated.

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