Skip to main content
Glama

learnjcu_update

Idempotent

Updates this MCP server copy from GitHub by previewing the git/npm plan, applying changes only after confirmation, and requiring a client restart.

Instructions

Update this copy of learnjcu-mcp to the latest version from GitHub (git fetch, switch to main and fast-forward, npm install). Only use after the user has said yes to updating. Always call with dryRun: true first, show the plan, then call with confirm: true. The user must restart the MCP client afterwards.

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": "learnjcu_update"
  }
}

Input Schema

NameRequiredDescriptionDefault
dryRunNoShow the plan without changing anything
confirmNoMust be true to actually send. Only set it after showing the user the dryRun plan and getting their explicit yes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare a non-read-only, open-world, non-destructive operation, and the description adds real value beyond them: the exact mutations performed (fetch, checkout/fast-forward, npm install) and the post-condition that the MCP client must be restarted. It does not cover failure modes, e.g. what happens to local uncommitted changes or a diverged branch during the fast-forward.

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 tight sentences, front-loaded with the action and mechanism, then the authorization gate, then the call sequence, then the post-step. Nothing is padded and nothing needs reordering.

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 mutating, open-world updater with only two optional booleans and no output schema, the description covers mechanism, authorization, call ordering, and the required restart. The remaining gap (error/rollback behavior) is not something an agent needs in order to invoke it correctly.

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 both booleans are already documented, and the description largely restates the dryRun-then-confirm sequencing found in the schema's confirm text. It does add that dryRun:true is a mandatory first call rather than an optional flag, which slightly sharpens the workflow beyond the schema.

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 states a specific verb and resource — update this copy of learnjcu-mcp from GitHub — and even itemizes the underlying steps (git fetch, switch to main and fast-forward, npm install). An agent can tell this apart from a read-only status/check tool, though the sibling learnjcu_check_update is never named as the pre-flight alternative.

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?

It gives a clear precondition ('Only use after the user has said yes to updating') and an explicit two-step call protocol: dryRun first, show the plan, then confirm:true. What is missing is the pointer to which tool to call beforehand to discover that an update exists.

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