Skip to main content
Glama

Golemreach

by io.github.aniripsaretro-max
OverviewDiscussionsAdmin

Buy from or sell to a merchant

golemreach_trade

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.

Exchange gold with an NPC merchant. Selling loot is how you afford potions and better gear, and it is the main reason to walk back to town.

Stand within 3 tiles of the merchant first — golemreach_where lists every shop with its coordinates, and golemreach_talk with "trade" makes them recite exactly what they buy and sell, which is the reliable way to learn their item ids and prices.

RETURNS: what changed hands and for how much.

COMMON FAILURES, all self-explaining: "not_for_sale" (this merchant does not deal in that item — the message lists what they do), "too_expensive" (it names the price and your gold), "out_of_range" (walk closer), "not_enough_capacity" (what you bought would weigh more than you can carry).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNoHow many. Default 1.
npcIdYesThe merchant, as a creature id like "n5" or a content id like "general_store".
itemIdYesItem id, e.g. "health_potion" or "rat_tail".
operationYesWhich way the goods go.
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

A4.8/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and delivers: it discloses four named failure modes with plain-language meanings (not_for_sale, too_expensive, out_of_range, not_enough_capacity), the 3-tile positional constraint, the return value ('what changed hands and for how much'), and the security implication of sessionId. This goes far beyond what any structured field provides.

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-organized — the critical sessionId warning is front-loaded, and the RETURNS and COMMON FAILURES sections are labeled for easy scanning. It loses a point because the sessionId paragraph duplicates the schema's sessionId description verbatim rather than adding new information.

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 5-parameter tool with no annotations and no output schema, this description is unusually complete: prerequisites, discovery workflow, return summary, and all common failure modes are covered. The RETURNS line compensates for the missing output schema by telling the agent exactly what to expect back.

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 the baseline is 3, and the description adds genuine value on top: it explains how to obtain valid values for npcId and itemId (via golemreach_where and golemreach_talk 'trade'), and the failure messages tie directly to parameter misuse. Count semantics are left entirely to the schema, which is acceptable but not enhanced.

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 title and description state a specific action and resource: 'Buy from or sell to a merchant' and 'Exchange gold with an NPC merchant.' Trading is unambiguously distinct from the sibling set (attack, cast, move, talk), and the description even clarifies the strategic purpose (selling loot to afford potions and gear).

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 prerequisites ('Stand within 3 tiles of the merchant first') and routes to the exact sibling tools for each discovery step: golemreach_where for shop coordinates and golemreach_talk with 'trade' to learn item ids and prices. It also frames when the tool matters (walking back to town to sell loot), leaving no inference needed.

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