Skip to main content
Glama

WNBA Elo ratings and win probability

invoke_wnba_elo
Read-onlyIdempotent

Added after you connected: the first call asks you to approve it. WNBA Elo ratings, calculated by BankrollSZN: margin Elo for every WNBA 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. view accuracy: log loss, Brier and margin MAE by season. Constants refit on WNBA history. Backtest 2024 to 2026 (905 games): log loss 0.5957 vs 0.6055 without the injury term. In the off-season, preseason_rating is next season's starting rating. 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_wnba_elo"
  }
}

Input Schema

NameRequiredDescriptionDefault
teamNoTeam abbreviation (NYL, LVA, ATL).
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

A4/5.0
Behavior4/5

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

Annotations already cover the read-only/idempotent/non-destructive profile, and the description adds genuinely new behavioral context: the first call triggers an approval prompt, ratings carry an injury term, constants are refit on WNBA history, and the tool is 'display only, not a betting signal' — a meaningful scope limit. It does not cover pagination/row-limit behavior beyond what the schema states, but the disclosure is well beyond the annotation baseline.

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?

It is front-loaded with the approval-prompt notice and then organized view by view, so each paragraph earns its place with concrete output detail. The backtest figures and 'Constants refit on WNBA history' sit mid-stream and could be tightened, but there is no filler or restatement of the name.

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 responsibility for explaining return values, and it does so per view with named fields (rank, record, change windows, predicted home margin, log loss/Brier/MAE). It is nearly complete for a read-only analytical tool; what remains thin is how limit/offset pagination interacts with the views and whether the team filter applies to all three views.

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 the baseline is 3, and the description earns the bump by mapping each view value to its concrete output content — rating/rank/record/7-30-day change for ratings, Elo win probability and predicted home margin ('positive = home favored') for games, log loss/Brier/margin MAE for accuracy. The team parameter gains no extra meaning beyond the schema's abbreviation examples, and limit/offset are left entirely to the schema.

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 names a concrete resource and its provenance ('WNBA Elo ratings, calculated by BankrollSZN') and enumerates three distinct views (ratings, games, accuracy) with the specific outputs of each. The league-specific framing plus the named views make it clear this is the WNBA Elo tool, though it never explicitly states the distinction from the sibling league Elo tools (invoke_nba_elo, invoke_mlb_elo, etc.), leaving that to inference from the name.

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?

It states the default ('view ratings (default)') and describes the situational context for each view — ratings for standings/form, games for today-to-two-days-out matchup probabilities, accuracy for model evaluation, plus an off-season caveat for preseason_rating. It gives no explicit exclusions or named alternative tools, so an agent must infer view selection from the described outputs rather than from a stated when-to-use rule.

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