Skip to main content
Glama

find_comps

Identify nearest player comps by comparing a prospect's college-stat archetype and showing known NBA outcomes for 'who does this remind you of' questions.

Instructions

Nearest neighbors to a player in archetype space (PCA over 12 standardized college stats), with their actual NBA outcomes when known. Good for "who does this remind you of" questions.

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": {
      "player": "<player>"
    },
    "name": "find_comps"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNo
playerYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does add genuine context: the similarity is computed via PCA on 12 standardized college stats, and outcomes are returned only 'when known', signaling possible nulls. It does not cover what happens if the player is absent from the dataset, identifier resolution, or the size/shape of the result beyond k.

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?

Two compact sentences with the mechanism and the use case front-loaded; no filler. The parenthetical methodology is information-dense rather than wasteful, so only minor tightening is possible.

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?

The method and output content are explained well for a simple two-parameter tool with no output schema. Gaps remain around the undocumented 'k' parameter, the player identifier format, and behavior on unknown players, which are the things an agent most needs before calling it.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate for both parameters, and it does not. 'k' is never mentioned, and the description never clarifies whether 'player' is a name, an ID, or a free-text string, leaving an agent to guess at identifier format and neighbor count 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?

The description gives a concrete operation and resource: nearest neighbors to a player in a defined 'archetype space' built from PCA over 12 standardized college stats, plus NBA outcomes. That is specific enough to distinguish it from lookup-style siblings like search_players or compare_prospects, though it never names a sibling explicitly.

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 offers one positive usage cue ('Good for "who does this remind you of" questions'), which is real but thin. There is no when-not guidance and no statement of how it differs from compare_prospects or get_skill_profile, so the agent must infer routing from the phrasing alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.