Skip to main content
Glama

Golemreach

by io.github.aniripsaretro-max
OverviewDiscussionsAdmin

What you know: where you have been, what you have killed, what you have been told

golemreach_where

Pass the sessionId returned by golemreach_connect with EVERY tool call, including after reconnecting. Keep it private: it grants control of your character. If you have no sessionId yet, call golemreach_connect once.

YOUR CHARACTER'S OWN KNOWLEDGE. Not a world directory — there is no world directory, and this is the single most important thing to understand about playing here.

This game does not publish a map. A place enters your knowledge when you WALK INTO IT; a monster enters it when you KILL ONE; a lead enters it when somebody TELLS YOU. So a brand new character calling this tool gets an empty list of hunting grounds, and that is correct, not broken.

WHEN THE LIST IS EMPTY, DO THIS: find any NPC in sight (the CREATURES list in a look, ids like "n3") and call golemreach_talk with text "where can I hunt?". Any NPC answers — a smith knows where the wolves are as surely as a priest does. They give you a LEAD: a name and a direction in words, deliberately with no coordinates. Walk that way until you find the place; arriving is what turns the lead into a real destination you can hand to golemreach_move. Calling this tool again instead of talking to somebody will return the same empty list forever.

CALL IT EARLY, AFTER EVERY CONVERSATION, AND WHENEVER YOU HAVE NOTHING TO FIGHT.

RETURNS: hunting grounds you have found (with travel coordinates and what YOU have killed there — not the spawn list, so an empty one means you have not fought there yet); leads you have been given; your quests and their objective counters; your bestiary, which grows in detail at 5 and at 25 kills of a kind; places you have walked past; and the towns, which are the one thing everybody always knows.

It is free, and it needs a character in the world — call golemreach_connect first.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
levelNoRank the hunting grounds for this character level instead of your own.
limitNoHow many hunting grounds to list. Default 5.
sessionIdNoPass the sessionId returned by golemreach_connect with EVERY tool call, including after reconnecting. Keep it private: it grants control of your character. If you have no sessionId yet, call golemreach_connect once.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / sessionId
      Added value: +{
+  "description": "Pass the sessionId returned by golemreach_connect with EVERY tool call, including after reconnecting. Keep it private: it grants control of your character. If you have no sessionId yet, call golemreach_connect once.",
+  "pattern": "^gs_[A-Za-z0-9_-]{43}$",
+  "type": "string"
+}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral disclosure burden, and it does so thoroughly. It explains that results are per-character, that an empty list is correct for a new character, that leads deliberately lack coordinates, that hunting grounds show personal kills rather than spawn lists, and that bestiary detail grows at 5 and 25 kills. It also discloses the security implication of sessionId and that the tool requires an active character.

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 description is long but well-structured with clear paragraphs, imperative guidance, and a return-category summary. Some redundancy exists, particularly repeating the sessionId instructions that already appear in the schema, but the added gameplay context is valuable enough to justify most of the length.

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?

Given the lack of annotations and output schema, the description is remarkably complete. It covers the tool's purpose, return categories, empty-result semantics, follow-up actions using sibling tools, when to call it, and authentication requirements. An agent has everything needed to call this tool correctly and interpret its results.

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?

The schema already documents all three parameters with 100% coverage, including the sessionId pattern and caveats. The description reinforces the sessionId security guidance but adds no new meaning for the level or limit parameters, so the baseline score of 3 is appropriate.

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?

The description states exactly what the tool does: it returns the character's own knowledge — hunting grounds, leads, quests, bestiary, places visited, and towns. It explicitly distinguishes itself from a world directory and from sibling tools like golemreach_talk and golemreach_move by describing how knowledge is acquired.

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?

The description gives explicit when-to-use guidance: call it early, after every conversation, and whenever there is nothing to fight. It also tells the agent when NOT to use it: if the list is empty, call golemreach_talk to ask an NPC for a lead instead of calling this tool again.

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

All Golemreach 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