Skip to main content
Glama

NBA Roster Shapes: Wyman diagrams

invoke_nba_roster_shapes
Read-onlyIdempotent

Added after you connected: the first call asks you to approve it. NBA Roster Shapes (Wyman diagrams), calculated by BankrollSZN. Shape system created by Taylormetrics (https://x.com/taylormetrics). Every team's top 10 rotation players by minutes, each with a shape for his role and a size for his value. Top tier: square (ideal star), hexagon (better passer than scorer, glue guy), octagon (star with a caveat). Offense first: circle (scores and passes, no defense), triangle (scorer or high-end shooter), diamond (good option with a flaw). Role: small square (3 and D), parallelogram (flawed 3 and D), arch (good defense, bad offense), pill (defensive big, no offense yet), rectangle (productive big), 4-point star (spot-up shooter, no defense). Size is value per game on one scale for all 30 teams. Percentiles for scoring, passing, 3PA rate, efficiency, usage and an estimated defense grade (box score rates and plus-minus, no tracking data). Give team for one roster, player for one player, or shape to list every player with that shape. Updated daily in season.

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_nba_roster_shapes"
  }
}

Input Schema

NameRequiredDescriptionDefault
teamNoTeam abbreviation (ESPN style: NY, SA, GS, NO, UTAH, WSH).
tierNoFilter by tier.
limitNoMaximum rows to return. The plan limit applies on top.
shapeNoList players with this shape.
offsetNoPaid plans: next page offset from page.next_offset.
playerNoPlayer name, or part of a name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
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 substantive traits: refreshed daily in season, values normalized to one per-game scale across all 30 teams, percentiles derived from box-score rates and plus-minus with no tracking data, and a first-call approval prompt. The only gap is that it doesn't describe response shape or how paging interacts with the plan limit.

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?

The opening is wasted on a meta note about approval plus attribution credits before any statement of purpose, and the shape taxonomy is delivered as one flowing run-on instead of a structured list. The content is informative but not front-loaded or scannable; an agent must parse the entire block to extract the query modes.

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?

For a read-only, six-parameter lookup with no output schema, the description covers data provenance, refresh cadence, the value scale, and the meaning of returned categories. What remains thin is pagination semantics and why a caller would choose this over the related rotation/pool tools.

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 descriptions for team, tier, shape, player, limit and offset are already supplied and the baseline is 3. The description does add real meaning by defining what each shape enum value signifies in basketball terms, which the schema's raw enum does not, but it offers nothing extra on limit/offset/pagination behavior.

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 concrete resource: every team's top-10 rotation players by minutes, each with a role shape and a value size, plus the three query modes (team, player, shape). It is clear what an agent gets back, but it never distinguishes this from adjacent siblings like invoke_nba_rotations or invoke_nba_player_pool.

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?

It does give mode-selection guidance -- 'Give team for one roster, player for one player, or shape to list every player with that shape' -- which tells the agent which parameter to use for which intent. However, there is no statement of when to prefer this tool over the rotation or player-pool tools, and no exclusions or prerequisites beyond the onboarding approval note.

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