Skip to main content
Glama
Sign In

Morris Golf

by golf.morris
OverviewDiscussionsAdmin

Suggest fantasy team

suggest_fantasy_team
Read-onlyIdempotent

Sugiere un equipo del fantasy de esta semana con sus motivos calculados en código: un profesional por tier según el ranking Badgie (nuestro, de golpes ganados al field en sus resultados recientes, ponderados por fecha y fuerza del field), forma reciente (puntos en sus últimos torneos del fantasy), cómo rinde en campos de esta longitud y en este mismo campo, y el capitán. include/exclude: profesionales que el jugador quiere o no quiere (nombre o id). No guarda nada: para guardarlo, save_fantasy_team. Cita los motivos tal cual; si ranking_only es true, di que aún no hay historial y que la sugerencia sigue el ranking.

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": "suggest_fantasy_team"
  }
}

Input Schema

NameRequiredDescriptionDefault
excludeNoProfessionals the player does not want, by name or id.
includeNoProfessionals the player wants, by name or id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / exclude / description
      Added value: +"Professionals the player does not want, by name or id."
    • addedInput schema / properties / include / description
      Added value: +"Professionals the player wants, by name or id."
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavior: reasons are computed in code rather than free-form, nothing is persisted, and the agent is told to quote the reasons verbatim and to explain the ranking-only case (no history yet) instead of implying form data exists. The reference to `ranking_only` is undocumented as either a parameter or a return field, which slightly muddies the disclosure.

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?

The action and the computed criteria are front-loaded in the first sentence, and every subsequent clause (include/exclude, no persistence, verbatim quoting, ranking-only caveat) earns its place. It loses a point for heavy nested parentheticals that make the single dense block harder to scan than a short bulleted sequence would be.

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 two-parameter read-only tool with no output schema, the description covers what is computed, that state is not saved, where to save instead, and how to present results, which is close to sufficient. The gaps are the unaddressed suggest_fantasy_squad sibling and the unexplained `ranking_only` reference.

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 description coverage is 100% and both parameters are already documented as name-or-id lists, so the description's restatement of include/exclude adds little beyond the schema. It does hint at why include is bounded (one professional per tier) but never spells out the tier logic or the effect of exceeding limits, leaving the schema to carry the parameter semantics.

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 specific verb and resource (suggest this week's fantasy team) and goes further by enumerating the computed criteria: Badgie ranking with strokes gained weighted by recency and field strength, recent form, course-length and same-course performance, and the captain. It does not, however, distinguish itself from the sibling suggest_fantasy_squad, which an agent could easily confuse with this tool.

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 gives real context: weekly scope, include/exclude for players the user wants or rejects, and an explicit hand-off ("No guarda nada: para guardarlo, save_fantasy_team"). What is missing is any exclusion or comparison against the near-identical sibling suggest_fantasy_squad, so the agent gets a when-to-save rule but not a when-to-use-this-vs-that rule.

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

All Morris Golf 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