Skip to main content
Glama

NFL showdown lineup optimizer

invoke_nfl_showdown_optimizer
Read-onlyIdempotent

Added after you connected: the first call asks you to approve it. Builds DraftKings NFL Showdown lineups: 1 CPT (1.5x points and salary) plus 5 FLEX under $50,000, with both teams in the lineup. gpp scores ceiling minus an ownership penalty; cash scores the projection. Built-in rules: a QB captain is stacked with his own pass catchers projected for 4 or more points (default 2 in gpp, 1 in cash), and a lineup never has 2 or more WR or TE from one team without that QB. For a game script use boost (for example ["JAX RB:20", "JAX DST:15", "BAL WR:-25", "Travis Etienne:10"]) and min_from_team (for example "JAX:4"), plus captain, lock and exclude. The search is exact unless it says it hit the node limit. Returns DK ids in slot order.

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_nfl_showdown_optimizer"
  }
}

Input Schema

NameRequiredDescriptionDefault
gameNoA game like JAX@BAL, instead of slate_id.
lockNoPlayer names that must be in every lineup.
modeNoDefault gpp.
boostNoScore changes in percent, as "target:percent". Target is a player name, a team (JAX), or a team and position (JAX RB, BAL DST). Negative fades. Range -60 to 60.
captainNoThe player to use at CPT.
excludeNoPlayer names to leave out.
lineupsNoNumber of lineups, 1 to 5. The free plan gets 1.
slate_idNoShowdown slate_id from nfl_list_slates. Default: the next showdown.
min_salaryNoLeast salary to use. Default 45,000.
min_uniqueNoSlots each lineup must differ from the ones before it. A captain swap counts. Default 2 for gpp, 1 for cash.
own_lambdaNoOwnership penalty in points per ownership percent for gpp. Default 0.15. 0 removes ownership.
max_per_teamNoMost players from one team. Default 5.
max_total_ownNoCap on the summed CPT and FLEX ownership of the lineup, in percent.
min_from_teamNoFewest players from one team, as "TEAM:count", for example "JAX:4" for a one-sided script.
include_kickersNoAllow kickers. Default true.
qb_cpt_pass_catchersNoOwn WR or TE needed with a QB captain. Default 2 for gpp, 1 for cash. 0 turns the rule off.
allow_pass_catchers_without_qbNoAllow 2 or more WR or TE from one team without that QB. Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare this a safe, idempotent read, and the description still adds substantial behavior: built-in stacking constraints, salary and CPT pricing rules, exact search unless the node limit is hit, a free-plan lineup cap of 1, and the fact that it returns DK ids in slot order. It also flags that the first call triggers an approval prompt, which prepares the agent for an interactive step.

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?

Dense but front-loaded: construction constraints first, then scoring modes, then rules, then tuning knobs, then output. Given 17 parameters this density is justified, though the opening approval-prompt sentence is awkwardly placed ahead of the actual purpose statement.

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 17-parameter optimizer with no output schema, the description carries the needed load: it states what comes back (DK ids in slot order), explains the search's exactness caveat, and documents the non-obvious scoring and stacking behavior an agent cannot infer from the schema alone.

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 earns above that by supplying concrete string formats for boost ("JAX RB:20", "BAL WR:-25") and min_from_team ("JAX:4") plus worked intuition for how each drives the search. Some of the built-in-rule text restates schema defaults, so it is not purely additive.

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?

Opens with a specific verb and resource — builds DraftKings NFL Showdown lineups — and immediately pins down the exact lineup construction (1 CPT at 1.5x points/salary plus 5 FLEX under $50,000, both teams represented). This is concrete enough that an agent can distinguish it from classic-format optimizers without inspecting any schema.

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?

Gives clear situational guidance for the tuning parameters — use boost with a game-script example and min_from_team for a one-sided script — and explains that gpp scores ceiling-minus-ownership while cash scores projection. It stops short of naming when to choose this over a sibling optimizer or when the tool is inappropriate.

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