Skip to main content
Glama

NBA Elo ratings and win probability

invoke_nba_elo
Read-onlyIdempotent

Added after you connected: the first call asks you to approve it. NBA Elo ratings, calculated by BankrollSZN: margin Elo for every NBA team with an injury term (value of missing rotation players moves the pregame rating gap). view ratings (default): rating, rank, record, change over 7 and 30 days and the season, and next season's carried rating (preseason_rating). view games: today to two days out with each team's rating, missing players, Elo win probability for each side and predicted home margin (positive = home favored), next to the market spread and market win probability. view accuracy: log loss, Brier and margin MAE by season and against the closing price. Backtest 2024-25 to 2026-27 (2,797 games): log loss 0.5948 vs 0.6045 without the injury term and 0.5791 for the closing line. Display only, not a betting signal.

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": "invoke_nba_elo"
  }
}

Input Schema

NameRequiredDescriptionDefault
teamNoTeam abbreviation, ESPN style (NY, SA, GS).
viewNoDefault ratings.
limitNoMaximum rows to return. The plan limit applies on top.
offsetNoPaid plans: next page offset from page.next_offset.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description still adds real context beyond them: the first call triggers an approval prompt, plan limits stack on top of the limit parameter, offset paging is for paid plans, and the output is display-only rather than a betting signal.

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 approval notice is front-loaded, but the purpose statement is buried behind it and the body is a dense run-on chain of colons. The backtest benchmark figures (2,797 games, log loss figures) are informative but border on promotional filler for a tool-selection description.

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, the description carries the return-value burden and does so for all three views, plus paging and the consent prompt. Only minor gaps remain, such as any error behavior or rate limits beyond the plan-limit note.

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 100% so baseline is 3, but the description meaningfully enriches the view enum (the schema only says 'Default ratings') by explaining each view's payload, and clarifies that the plan limit applies on top of the limit parameter.

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 (NBA Elo ratings calculated by BankrollSZN) and disambiguates its three modes by naming exactly what each returns: ratings with rank/record/7-30-day change/preseason rating, games with win probability and predicted home margin vs market, and accuracy with log loss/Brier/MAE.

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?

Clearly implies when to pick each view (ratings marked as default, games for today-to-two-days-out matchup data, accuracy for model benchmarking) and ends with a scoping caveat ('Display only, not a betting signal'). It stops short of naming when to prefer a sibling such as injury or projection tools, so it is not a full 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources