Skip to main content
Glama

FastballAPI

Alt lines

get_alt_lines
Read-onlyIdempotent

Use for alternate run lines and totals by sportsbook: every point on each book's ladder with its price (e.g. -2.5 at +190, over 9.5 at +140), for one game. Held for MLB games from the 2023 season on, from five books (DraftKings, FanDuel, BetMGM, Bovada, Pinnacle). Games before Nov 12 2026 were captured once shortly before first pitch, so their opening and closing ladders are the same; from Nov 12 2026 upcoming games are captured up to three times a day before the start. Games not yet priced have none. Returns each book's closing ladder by default (its last before the start) or its opening one. side is home or away for run lines (point is that side's run line) and over or under for totals. For the main line use get_odds. 10 credits. Prices are market information; no tool places, accepts or tracks wagers.

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": {
      "game_id": "<game_id>"
    },
    "name": "get_alt_lines"
  }
}

Input Schema

NameRequiredDescriptionDefault
leagueNoLeague. Defaults to mlb. One of: mlb, ncaabase.
marketNoOne market (default both).
game_idYesGame id, e.g. 776512 (from get_games or get_schedule).
bookmakerNoOne bookmaker key, e.g. draftkings, fanduel.
snapshot_typeNoClosing (default) or opening ladder.

Output Schema

NameRequiredDescriptionDefault
noteNo
countYes
linesYes
leagueYes
game_idYes
snapshot_typeYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds real value beyond that with snapshot cadence (once shortly before first pitch before Nov 12 2026, up to three times a day after), the fact that opening and closing ladders coincide for older games, default-to-closing behavior, and a 10-credit cost. It also clarifies that prices are market information and no wagering occurs. It stops short of describing pagination or response size, but the return structure is covered by the output schema.

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?

The core capability and the get_odds routing are front-loaded in the first two sentences, and the coverage/cadence caveats follow logically. It is a dense single block with some run-on clauses (the capture-cadence sentence in particular), but no sentence is filler given the unusual data-coverage rules.

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 five-parameter, read-only odds tool with an output schema and full schema coverage, the description supplies everything else an agent needs: historical coverage window, book list, capture frequency, empty-result condition, default snapshot, credit cost, and the sibling to use for main lines. Nothing material is left to inference.

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; the description still adds meaning by defining what 'closing' means (the book's last ladder before the start) and by explaining that side distinguishes home/away for run lines versus over/under for totals. It also confirms defaults (closing ladder, one market vs both). Minor gap: 'side' is described without an explicit tie to a field the agent will see.

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 specific verb+resource: alternate run lines and totals by sportsbook, returning every point on each book's ladder with its price, for one game. It concretely differentiates itself from get_odds by stating that get_odds covers the main line. An agent can identify the tool's output shape without opening the schema.

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?

It names the alternative explicitly ('For the main line use get_odds') and gives the condition that selects it. It also states availability boundaries — MLB 2023 onward, five specific books, and 'Games not yet priced have none' — so the agent knows when the tool will return empty rather than guessing.

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.