Skip to main content
Glama

ParlayAPI

by io.github.JacobiusMakes

parlayapi_best_bets

What should I bet right now? Ranked +EV plays for a sport.

The discovery counterpart to parlayapi_verdict: scans the whole board,
grades every candidate with the same no-vig engine, keeps only bets that
are +EV at a book the user can bet at, and ranks them by edge. Also returns
edge_alerts (books showing a price far off the market). Player props only,
priced by several books, prediction markets and game moneylines excluded
(for a game line, use parlayapi_verdict). Scoped to the user's books.

Args:
    sport_key: e.g. "baseball_mlb".
    region: us (default) | eu | uk | au | ca.
    books: exact CSV of books you can bet at (overrides region).
    limit: max plays to return (default 20).
    min_edge: minimum edge %% vs the no-vig fair line (default 2.0).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
booksNo
limitNo
regionNo
min_edgeNo
sport_keyYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A5/5.0
Behavior5/5

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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly. It discloses the scanning behavior, no-vig grading, +EV filtering, ranking logic, edge_alerts return, scoping to user books, and the player-props-only restriction. This gives the agent a realistic model of what the tool does beyond the bare schema.

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?

The description is well structured: the purpose is front-loaded, the sibling relationship is explained next, and the Args block maps directly to the schema. Every sentence adds substantive information, with no filler or repetition.

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 discovery tool with an output schema present, the description covers input semantics, scope, exclusions, and sibling alternatives completely. An agent has everything it needs to decide when to invoke the tool and how to populate parameters correctly.

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

Parameters5/5

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

Schema description coverage is 0%, but the description documents all five parameters with defaults, allowed values, and semantic context. For example, it explains that min_edge is a percentage against the no-vig fair line and that books overrides region, which is far more useful than the bare schema names.

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?

The description opens with a clear value proposition ('What should I bet right now? Ranked +EV plays for a sport') and names the resource and action precisely. It explicitly identifies itself as the discovery counterpart to parlayapi_verdict, which differentiates it from the closest sibling without requiring schema inspection.

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

Usage Guidelines5/5

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

The description states exactly when to use this tool: for discovery across the whole board, filtering to +EV plays at the user's books, and ranking by edge. It also provides clear exclusions and routes users to parlayapi_verdict for game moneylines, giving explicit when-to-use and when-not-to-use guidance.

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

All ParlayAPI toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation3/5

Most tools map to distinct workflows (raw odds, best-line, EV scan, arb, middle, single-bet grade, parlay grade), but several pairs are easy to mix up: find_ev vs best_bets both surface +EV opportunities, live_sports vs list_sports differ only in 'live', and verdict vs parlay_verdict have near-identical names. The detailed descriptions resolve most ambiguity, so it is not chaotic, but the boundaries are not all crisp.

Naming Consistency3/5

All names share the parlayapi_ prefix and snake_case, but the suffix style is inconsistent: some are verb-led (get_odds, find_arbitrage, set_bettable_books) and many are bare noun phrases (consensus, verdict, source_quality, magic_link). The live_* and best_* groups are internally consistent, but pairs like list_sports/live_sports and verdict/parlay_verdict add confusion.

Tool Count3/5

22 tools is on the heavy side for an MCP server, even though the sports-betting domain is broad. Each tool has a plausible purpose, but the public demo/metadata tools (live_command_center, book_coverage, source_quality, live_sports) could probably be consolidated or separated.

Completeness4/5

The surface covers the core domain well: sport discovery, game odds, props, consensus, best-line, EV, arbitrage, middles, single-bet verdicts, parlay verdicts, and account/signup flows. Minor gaps exist (no explicit book/market metadata list, no historical odds, no betting-account history), but agents can usually work around them.

Resources