Skip to main content
Glama

Similar Players, Milestones & Comparable Matchups

player_comparables
Read-onlyIdempotent

Use this when the user asks which players are most like a given player this season, how often a player reaches a number (20 points, 10 rebounds, a double-double; with or without a teammate), or how players of his position did against his next opponent lately. Returns, for a player_id, the players most like him by Keel Impact and role (NFL: by his group's main numbers), his milestones (NBA: the share of games reaching each mark), and (NBA) his position group against the next opponent over its last games: the record against the closing line for every caller, each game's row with Keel Stats Pro (account.held says when it was left out). Not for his own averages: use player_profile.

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": {
      "league": "<league>",
      "player_id": "<player_id>"
    },
    "name": "player_comparables"
  }
}

Input Schema

NameRequiredDescriptionDefault
statNoOptional NBA stat code for the comparable matchup ("pts" default, "reb", "ast", "tpm", "pra"…).
leagueYesLeague ("nba" or "nfl").
seasonNoOptional season year. Defaults to the current season.
player_idYesNumeric player ID from search.
without_player_idNoOptional, NBA milestones: only the games this teammate missed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, non-destructive behavior, so the description rightly spends its words elsewhere. It adds genuine behavioral context: league-dependent outputs (NFL groups by main numbers; NBA milestones and opponent matchups), that milestone values are shares of games rather than counts, and that some game rows may be withheld from the Keel Stats Pro comparison — a caveat an agent could not infer from annotations.

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 trigger clause is well front-loaded, but the "Returns…" sentence is a dense multi-clause run that stacks three result types and then trails into a cryptic clause about "the record against the closing line for every caller, each game's row with Keel Stats Pro." The phrase "every caller" and the inline `account.held` reference are jargon an agent must decode, which weakens otherwise efficient packaging.

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 no output schema and five parameters, the description carries the full burden of return-value explanation, and it does describe the three result sections and their league dependence. The only real gap is the opaque closing-line and `account.held` wording, which leaves the shape of that particular section under-specified for an agent that must report results.

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, but the description goes beyond it by tying parameters to capability branches: "with or without a teammate" corresponds to without_player_id, the NBA/NFL split determines which return sections exist, and the stat code's role is limited to the comparable matchup. That mapping helps an agent decide which parameters matter for a given request.

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 enumerates three concrete capabilities with specific resources: most-similar players by Keel Impact and role, milestone frequency shares, and position-group performance against the next opponent. It also states what the resource is not ("Not for his own averages: use player_profile"). The bundling of three modes makes the tool's overall identity slightly diffuse, but each mode is stated precisely enough to act on.

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?

Each capability is gated by an explicit user-question trigger ("which players are most like a given player this season", "how often a player reaches a number… with or without a teammate", "how players of his position did against his next opponent lately"). One exclusion is given with the correct alternative named (player_profile for his own averages). No further exclusions are stated, but the when-to-use coverage is clear.

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