Skip to main content
Glama

league-loom

by com.leagueloom
OverviewDiscussionsAdmin

Get All My Teams (across every league)

fantasy_get_my_teams
Read-onlyIdempotent

Your personal scoreboard and kickoff check across connected teams. ALWAYS render a separate section for EACH team, labeled with team and league; never mix players or points across teams. Default view=scoreboard returns only personal matchups with compact starter highlights, verified game-progress coverage and actual score changes when comparison_snapshot from a previous response is supplied. Use view=kickoff for "am I ready for kickoff", empty slots, injury checks, deadlines and replacement options in each league. Use view=summary for lighter standings and totals. Keep comparison_snapshot private and pass it unchanged on the next refresh; it expires after 24 hours and cannot authorize any account access. Use for anything plural or cross-league ("my teams", "how am I doing", "my week"; pass sport for "my football teams") — do NOT answer those from one league. Needs a connected profile. For one named league's detail, fantasy_get_my_team.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
viewNoscoreboard: compact live scoring per team; kickoff: lineup readiness plus injuries and replacement options; summary: lighter standings and totals.scoreboard
sportNoOptional: only this sport, e.g. 'NFL' for 'my football teams'. Omit for ALL sports.
providerNoOptional: only this provider. Omit to aggregate across all.
league_queryNoOptional: exactly one configured league. Omit for all matching teams.
response_formatNo'markdown' (default) or 'json' (raw payload).markdown
comparison_snapshotNoOpaque comparison_snapshot from the previous response to this same connection. Pass unchanged for actual score changes; never fabricate it or show it to the user.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / comparison_snapshot
      Added value: +{
+  "description": "Opaque comparison_snapshot from the previous response to this same connection. Pass unchanged for actual score changes; never fabricate it or show it to the user.",
+  "maxLength": 65536,
+  "type": "string"
+}
    • addedInput schema / properties / league_query
      Added value: +{
+  "description": "Optional: exactly one configured league. Omit for all matching teams.",
+  "type": "string"
+}
    • addedInput schema / properties / view
      Added value: +{
+  "default": "scoreboard",
+  "description": "scoreboard: compact live scoring per team; kickoff: lineup readiness plus injuries and replacement options; summary: lighter standings and totals.",
+  "enum": [
+    "summary",
+    "scoreboard",
+    "kickoff"
+  ],
+  "type": "string"
+}
  2. Changed2 schema fields changed
    • changedInput schema / properties / provider / description
      Previous value: -"Optional: only this provider. Omit to aggregate across Fantrax, ESPN, and Sleeper."New value: +"Optional: only this provider. Omit to aggregate across all."
    • changedInput schema / properties / response_format / description
      Previous value: -"Output format: 'markdown' (default, human-readable) or 'json' (raw upstream payload)."New value: +"'markdown' (default) or 'json' (raw payload)."
  3. First observed

TDQS

A4.6/5.0
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 genuinely new behavior: comparison_snapshot expires after 24 hours, cannot authorize account access, and must be kept private and passed unchanged. It does not describe pagination or result-size limits, so not a full 5.

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?

Front-loads the most important behavioral rule (render a separate section per team) and keeps one idea per sentence. It is dense and mixes render instructions with parameter guidance, which lengthens it slightly beyond strict necessity, but every sentence carries actionable content.

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?

With no output schema, the description carries the return-shape burden and does so: it describes what each view returns (compact starter highlights, game-progress coverage, standings/totals) and the per-team section formatting requirement. Nothing needed to call it correctly is missing.

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 description coverage is 100%, so the baseline is 3; the description adds meaning beyond the schema by explaining the snapshot's 24-hour expiry and its non-authorizing nature, and by giving the 'my football teams' example for the sport param. It largely restates the view enum semantics already documented in the schema.

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?

States a specific verb+resource ('Your personal scoreboard... across connected teams') and explicitly scopes it as plural/cross-league, distinguishing it from the singular sibling 'For one named league's detail, fantasy_get_my_team.' The three view modes are named and given distinct meanings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit routing: use for anything plural or cross-league, pass sport for 'my football teams', and points to fantasy_get_my_team for a single named league. Each view has a stated purpose ('view=kickoff for am I ready for kickoff, empty slots, injury checks').

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

All league-loom toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources