Skip to main content
Glama

NHL Player Index: player vs system value

invoke_nhl_player_index
Read-onlyIdempotent

Added after you connected: the first call asks you to approve it. NHL Player Index, calculated by BankrollSZN: splits each player's DraftKings points per 60 minutes of ice time into player_value (above an average player on an average team), system_lift (what the current team adds) and the rest, with a trend vs the season before, a star with / without split and an archetype: Difference maker, System product, Rising, Blocked by teammates, Fading, Neutral. Groups: F (forwards), D (defensemen), G (goalies). Extra: top linemates and the linemate lift, power play share (goalies: start rate) and share of team games. Backtest skaters: error 4.34 vs 4.38 for a regressed last-season baseline. The backtest covers 2024-25 to 2026-27 only. view players (default; give player for one player with season history), systems (team lift, latest season) or step_up (biggest gains when the team's star sits). Ridge model on regular season data since 2024-25. A ranking of who is real and who rides the team, not a nightly projection.

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_player_index"
  }
}

Input Schema

NameRequiredDescriptionDefault
teamNoTeam abbreviation.
viewNoDefault players.
groupNoplayers view: only this group.
limitNoMaximum rows to return. The plan limit applies on top.
offsetNoPaid plans: next page offset from page.next_offset.
playerNoPlayer name, or part of a name.
sort_byNoplayers view sort. Default player_value.
sort_dirNoDefault desc.
archetypeNoplayers view filter.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely non-obvious behavior: the first call triggers an approval prompt, the model is a Ridge regression on regular-season data since 2024-25, and the backtest only covers 2024-25 to 2026-27 with a stated error of 4.34 vs 4.38. Disclosing the limited backtest window and the approval prompt is exactly the kind of context annotations cannot convey; the gap is that it never says what the response payload looks like or how limits behave beyond what the schema states.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is one dense run-on block with a strange administrative sentence ('Added after you connected: the first call asks you to approve it') leading, which buries the actual purpose. Most sentences do carry information, but the cramming of backtest metrics, archetype labels and view modes into a single paragraph hurts scannability.

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

Completeness4/5

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

With 9 optional parameters, no output schema, and 100% schema coverage, the description does the heavy lifting well: it explains the metric components, the three views, the group codes, and the extra fields (linemates, power play share, team game share). Missing are caveats on how the plan limit interacts with returned rows and what the pagination fields look like, but overall it is complete enough to call correctly.

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 baseline is 3, but the description earns more by explaining what each view returns and by expanding the group codes into 'F (forwards), D (defensemen), G (goalies)' and the archetype taxonomy. It also clarifies that passing a player yields season history rather than a filtered list. It does not explain sort_by fields like system_share or step_up_without_star beyond their 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 names a specific artifact (an NHL player index computed by BankrollSZN) and enumerates exactly what it decomposes into: player_value, system_lift, trend, star with/without split, and archetype. It also explicitly contrasts itself with adjacent tools by saying it is 'a ranking of who is real and who rides the team, not a nightly projection,' which separates it from the projections siblings.

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 concrete routing between the three views: 'players (default; give player for one player with season history), systems (team lift, latest season) or step_up (biggest gains when the team's star sits).' That is enough to pick a view and know when to pass a player. It stops short of naming when to prefer a sibling tool such as player_matchup or projections, so no explicit exclusions.

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