Skip to main content
Glama

FanDuel lineup optimizer

invoke_fd_optimizer
Read-onlyIdempotent

Added after you connected: the first call asks you to approve it. Builds FanDuel lineups with an exact search. NBA: PG, SG, SF, PF, C, G/F, F/C, UTIL, UTIL under $60,000, at most 4 per team. PGA: 7 golfers under $60,000 (FanDuel drops the lowest score; this tool scores all 7). NFL: QB, RB, RB, WR, WR, WR, TE, FLEX, DEF under $60,000, at most 4 per team, QB stacked with at least stack_size of his own WR or TE, no DEF against your QB. gpp scores ceiling minus an ownership penalty; cash scores the projection. Locks, excludes, several unique lineups, a salary floor and an ownership cap. Use only when the user asks for FanDuel.

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": {
      "sport": "<sport>"
    },
    "name": "invoke_fd_optimizer"
  }
}

Input Schema

NameRequiredDescriptionDefault
lockNo
modeNoDefault gpp.
sportYesnba, pga or nfl.
excludeNo
lineupsNoNumber of lineups, 1 to 5. The free plan gets 1.
slate_idNoslate_id from fd_slates. Default: the first Full Roster slate.
min_salaryNoLeast salary to use. Default 57,000 (NBA, NFL) or 56,000 (PGA).
min_uniqueNoPlayers each lineup must differ from every lineup before it. Default 2 for gpp, 1 for cash.
own_lambdaNoOwnership penalty in points per ownership percent for gpp. Default 0.1. 0 removes ownership.
stack_sizeNoNFL: own WR or TE needed with the QB. Default 1. 0 turns it off.
max_per_teamNoMost players from one team. Default 4.
max_total_ownNoCap on summed ownership in percent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
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, yet the description still adds real behavior: an approval gate on the first call, the exact scoring model for gpp versus cash, and the hard roster/salary/team-limit rules per sport. It stops short of saying what an infeasible constraint set returns or whether output ordering is deterministic.

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?

Front-loaded with the highest-value operational fact (first-call approval), then dense but non-redundant rule text. The per-sport roster enumerations are long, though each carries distinct constraint information that affects the result.

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

Completeness3/5

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

For a 12-parameter, no-output-schema optimizer the description covers inputs and contest rules well, but it never states what comes back (lineup objects? player lists? salary totals?) or how failures are surfaced. With no output schema, that return-shape gap is the notable omission.

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 already 83%, but the description still adds meaning the schema lacks: scoring implications of own_lambda ('ceiling minus an ownership penalty'), the purpose of locks/excludes, uniqueness across successive lineups, and the NFL stack rule. It does not clarify how max_total_own interacts with the gpp penalty, which is the main semantic gap.

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?

States a specific verb+resource: 'Builds FanDuel lineups with an exact search', and the closing 'Use only when the user asks for FanDuel' separates it from the DK-style/per-sport siblings. It does not explain why an agent would pick this over invoke_nba_optimizer or invoke_nfl_optimizer, so sibling differentiation is only partial.

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

Usage Guidelines3/5

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

There is one explicit restriction ('Use only when the user asks for FanDuel') and an operational warning about the first-call approval prompt. However, no positive conditions are given for when this multi-sport optimizer is preferred over the sport-specific optimizer siblings, leaving routing to inference.

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