Skip to main content
Glama

NS Pros MCP Gateway

golfcore__ask_caddie

Ask GolfCore's caddie a question about the shot the golfer is standing over, such as which club to hit or where to aim. Pass the question in their words, and lat and lng only if your device gives you their GPS position; otherwise GolfCore uses the position from the GolfCore app on their phone. The caddie reads the distance to the flag, the hazards and trees on the line, wind modeled for the terrain, the elevation change, and the golfer's own handicap and club distances from their GolfCore accoun

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": {
      "question": "<question>"
    },
    "name": "golfcore__ask_caddie"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNoOptional. The golfer's precise latitude, only when your device gives you their GPS position. Never ask the golfer for coordinates: leave lat and lng out and GolfCore uses the position from the GolfCore app on their phone.
lngNoOptional. The golfer's precise longitude, with lat.
holeNoOptional. The hole number the golfer says they are on. Otherwise the hole is chosen from the position.
courseNoOptional. The course slug, when known. Otherwise the course is found from the position.
questionYesThe golfer's question, in their words.
accuracy_mNoOptional. The location's horizontal accuracy in meters, when the device reports it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose the important hidden behavior: when lat/lng are omitted, GolfCore falls back to the position from the golfer's phone app, and the caddie pulls flag distance, hazards, terrain-modeled wind, elevation, and account handicap/club distances. Gaps remain: it never says what the answer looks like (format/length), and it is silent on any account or premium prerequisite despite a subscribe_premium sibling existing.

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-loaded with the purpose and concrete examples, then the usage constraint, which is the right order. Deductions for the long third sentence enumerating data inputs and for the text being visibly truncated mid-word ("from their GolfCore accoun"), which weakens polish and leaves the final clause incomplete.

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?

For a six-parameter, no-annotation, no-output-schema tool, the description explains the data sourcing and the location fallback well enough to call it correctly. It is not complete on the outcome side: nothing indicates the shape or basis of the returned advice, nor any account tier or rate constraints, leaving the agent to guess what it gets back.

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%, so the baseline is 3; every parameter is already documented in the schema, and the description largely restates the question and lat/lng semantics. It adds no meaning for hole, course, or accuracy_m, and no format hints for coordinates beyond what the schema provides.

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 and resource ("Ask GolfCore's caddie a question") scoped to a concrete situation ("the shot the golfer is standing over") and gives two example intents (which club, where to aim). The follow-on sentence enumerates the inputs the caddie considers, so an agent can tell this is a synthesized recommendation rather than a raw measurement like golfcore__distance_to_flag.

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?

Clearly frames the triggering situation (golfer asking a shot-selection or aim question) and gives an explicit negative rule: pass lat/lng only if the device supplies GPS, and never ask the golfer for coordinates. It stops short of naming an alternative tool or stating what to do for non-shot questions (e.g., general course queries), so routing guidance is not quite complete.

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.