HaterPicks API

Get live scores

get_scores

Read-onlyIdempotent

Live scores for 120+ leagues: score, period, clock and status for every game around today (yesterday's finals to two days ahead). With no league it lists the league keys. Golf and motor racing add a top-10 leaderboard. Works on every plan, Free included. A box score (game) needs Starter or higher. Counts as one API call (GET /api/v1/scores).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_scores"
  }
}

Input Schema

Name	Required	Description
`game`	No	A game id from the league's scores, for its box score (WNBL and NBL1; needs Starter or higher). Needs league.
`league`	No	League key, e.g. nba, afl, nrl, eng.1, wnbl. Leave it off for the list of every league key.
`season`	No	"current" for every game of the season, played and to come (WNBL and NBL1). Needs league.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations only establish the read-only/idempotent safety profile; the description adds real behavior: the date window (yesterday's finals to two days ahead), golf and motor racing returning a top-10 leaderboard instead of a game list, the plan tier required for box scores, and the cost of one API call against GET /api/v1/scores.

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?

Five short sentences, front-loaded with the core purpose and coverage, then time window, special cases, plan tiers, and cost. No sentence is redundant and each carries distinct operational information.

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

Completeness5/5

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

For a zero-required-parameter read tool with no output schema, the description covers what is returned, the time range, the special leaderboard shape, and access prerequisites. An agent has everything needed to call it correctly on the first attempt.

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 coverage is 100%, so all three parameters are already documented, including the dependency that 'game' and 'season' need 'league'. The description reinforces the no-league case but adds little beyond what the schema states, so the baseline 3 applies.

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 resource (live scores for 120+ leagues) plus the exact fields returned (score, period, clock, status), and scopes it to a time window. That is clearly distinguishable from siblings like get_odds or get_player_props without opening any 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?

Gives concrete selection rules: omit 'league' to list every league key, and 'game' or 'season' require a league. Plan gating (box score needs Starter or higher, everything else works on Free) is stated explicitly. It does not name a sibling as the alternative for betting-market queries, so it falls short of a 5.

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

All HaterPicks API tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?