Skip to main content
Glama
Sign In

Morris Golf

by golf.morris
OverviewDiscussionsAdmin

Ask morris

ask_morris
Read-only

Ask Morris, the player's golf caddie, one golf question and get a written answer built from their own data, their memories and the Morris playbook. Use it for judgement: what to practise, how to play a course, what a figure means. For a figure itself call the read tool that holds it (get_handicap, list_rounds, get_scorecard_stats). Uses one turn of the player's daily chat allowance. Read-only: it never saves or changes anything.

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": {
      "message": "<message>"
    },
    "name": "ask_morris"
  }
}

Input Schema

NameRequiredDescriptionDefault
messageYesThe question, written to stand alone: add the context Morris needs (club, course, what happened). Plain text, up to 4000 characters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / message / description
      Added value: +"The question, written to stand alone: add the context Morris needs (club, course, what happened). Plain text, up to 4000 characters."
  2. First observed

TDQS

A4.7/5.0
Behavior4/5

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

The annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond them: the call consumes one turn of the player's daily chat allowance (a quota cost an agent must budget for) and that it never saves or changes anything. It stops short of describing response length or what happens when the allowance is exhausted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with what the tool is, then what it is for, then the alternative, then the cost. Every sentence carries distinct information — purpose, use cases, routing rule, quota — and there is no restatement of the name or annotations.

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?

For a single-parameter, no-output-schema tool wrapped in annotations, the description covers everything an agent needs: purpose, discriminating use cases, the sibling alternatives for factual lookups, and the per-call allowance cost. Nothing required for a correct invocation 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, and the description adds modest value on top: 'one golf question' signals single-question scope and 'written answer' clarifies that the message is a prompt rather than a filter. It doesn't add formatting or phrasing guidance beyond the schema's own 'written to stand alone' note.

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 Morris one golf question, get a written answer) and immediately explains what the answer is composed from: the player's own data, memories and the Morris playbook. It also explicitly demarcates itself from the data-read siblings by naming get_handicap, list_rounds and get_scorecard_stats as the tools for raw figures.

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 an explicit when-to-use rule ('use it for judgement: what to practise, how to play a course, what a figure means') and an explicit when-not ('for a figure itself call the read tool that holds it'), with three concrete alternatives named. An agent can route between this and the sibling read tools without inference.

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