Skip to main content
Glama

NHL showdown lineup optimizer

invoke_nhl_showdown_optimizer
Read-onlyIdempotent

Added after you connected: the first call asks you to approve it. Builds DraftKings NHL Showdown lineups for one game: 1 CPT (1.5x points and salary) plus 5 UTIL under $50,000, with players from both teams. gpp scores ceiling minus an ownership penalty; cash scores the projection. Goalie rule: by default no skater faces the goalie in your lineup (the goalie goes with his own skaters only); max_skaters_vs_goalie changes that. Unconfirmed goalies are left out unless allow_unconfirmed_goalie is true. Supports a captain, locks, excludes, several unique lineups, a salary floor, an ownership cap and a per-team cap. The search is exact. Returns DK ids in slot order CPT, UTIL x5. Data refreshes every 30 minutes. DraftKings scoring.

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_nhl_showdown_optimizer"
  }
}

Input Schema

NameRequiredDescriptionDefault
gameNoA game like NSH@ANA, instead of slate_id.
lockNoPlayer names that must be in every lineup.
modeNoDefault gpp.
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 nhl_list_slates. Default: the first showdown slate of the day.
min_salaryNoLeast salary to use. Default 45,000.
min_uniqueNoSlots each lineup must differ from every lineup 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 UTIL ownership, in percent.
require_goalieNoEvery lineup has a goalie. Default false.
max_skaters_vs_goalieNoMost skaters allowed against the goalie in your lineup. Default 0.
allow_unconfirmed_goalieNoAllow goalies whose start is not Confirmed or Likely. Default false.

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 declare readOnly, idempotent, non-destructive, so they align with a pure solver; the description then adds substantial behavior the annotations cannot convey: the search is exact, unconfirmed goalies are silently dropped unless allow_unconfirmed_goalie is true, the default no-skater-vs-goalie rule, data refreshes every 30 minutes, and the return shape 'DK ids in slot order CPT, UTIL x5'. The leading meta sentence about an approval prompt is vague and slightly distracting rather than informative.

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 purpose, format, and salary cap are front-loaded in the second sentence, and the remaining clauses each carry a distinct rule (scoring modes, goalie defaults, optional constraints, return order, data freshness). The opening 'Added after you connected: the first call asks you to approve it' is meta filler that does not help an agent decide or invoke anything.

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 15-parameter tool with no output schema and all-optional params, the definition covers the essentials: lineup construction, salary constraint, mode-dependent scoring, the non-obvious goalie defaults, and the exact return format in slot order. An agent can call it correctly and interpret the result without further context.

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

Parameters3/5

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

Schema coverage is 100%, so all 15 parameters are already described in the schema, and the prose largely restates them ('a captain, locks, excludes, several unique lineups, a salary floor, an ownership cap and a per-team cap'). It does add interpretive context for the goalie-related parameters and the CPT salary multiplier, but nothing beyond that raises it above the baseline for a fully documented 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 first substantive sentence names a concrete verb and artifact: 'Builds DraftKings NHL Showdown lineups for one game: 1 CPT (1.5x points and salary) plus 5 UTIL under $50,000, with players from both teams.' That is precise enough that an agent understands both the format and the cap structure without opening the schema. It stops short of 5 because it never distinguishes itself from siblings such as invoke_nhl_showdown or invoke_nhl_optimizer, which presumably cover adjacent formats.

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 gives real selection context: gpp vs cash is explained by scoring model ('gpp scores ceiling minus an ownership penalty; cash scores the projection'), and the goalie rules clarify lineup-construction behavior. What is missing is any explicit exclusion or pointer to an alternative tool when showdown is the wrong format. This is clear context without routing.

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