Skip to main content
Glama

Check and update the Gameye skills

gameye_update_skills
Idempotent

Compares installed Gameye agent skills with the GitHub skills pack and optionally runs each outdated install's updater; defaults to check-only and changes nothing.

Instructions

Works without a Gameye account or token. Compare the installed Gameye agent skills with the latest pack on GitHub, and update them. Finds installs made with the skills CLI (user-wide or in this project) and the Claude Code plugin gameye@gameye. Without apply it only checks and changes nothing. With apply=true it runs each outdated install's own updater (npx skills update for the Gameye skills only, or claude plugin update) when the operator set GAMEYE_ENABLE_SKILLS_UPDATE=1; otherwise it lists the commands for the user to run. Ask the user before applying. Also reports the skills pack bundled with this server (1.7.1). Updates come only through those package managers. This server ships a pinned copy of the skills reviewed at build time; the skill and template tools never fetch skill text at runtime, and only gameye_update_skills reaches GitHub, when called.

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": "gameye_update_skills"
  }
}

Input Schema

NameRequiredDescriptionDefault
applyNoRun the updates for outdated installs. Omit or false to only check.
installedVersionNoThe `Pack version:` from the gameye skill you have loaded, used when no install is found on disk

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.3

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations: no account or token needed, exactly which commands run under apply, the env-var gate that decides whether commands execute or are merely printed, and that this is the only tool reaching GitHub and only when called. The annotations already declare openWorldHint=true and destructiveHint=false; the description corroborates and enriches that with the actual network and mutation mechanics.

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 core action and the safe default before the mechanics, which is the right ordering. The closing sentence about the pinned build-time copy is longer than it needs to be and slightly redundant with the earlier "only reaches GitHub, when called" point.

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 two-parameter, no-output-schema tool with an env-var gate, the description covers invocation modes, prerequisites, side effects, and what gets reported back. Nothing an agent needs in order to call it correctly or safely 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?

With 100% schema coverage the baseline is 3, but the description adds real meaning to apply — check-only by default, real updates only with apply=true and only when the operator opted in. installedVersion is not explained in the description, though the schema covers it and the mention of the bundled pack (1.7.1) hints at the version notion.

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 pair and resource: "Compare the installed Gameye agent skills with the latest pack on GitHub, and update them." It also scopes what counts as an install (skills CLI user-wide or project-level, plus the Claude Code plugin gameye@gameye), which separates it from the bundled-skill tools like gameye_list_skills and gameye_get_skill.

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?

Explicit branching guidance: "Without apply it only checks and changes nothing. With apply=true it runs each outdated install's own updater..." It names the prerequisite (GAMEYE_ENABLE_SKILLS_UPDATE=1) and the fallback behavior when unset, and gives a direct instruction to ask the user before applying.

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