Skip to main content
Glama
Path of Building MCP Server

Path of Building MCP Server

by urbanvcode

profile_set

Updates player profile fields—league, currency, play mode, goals, experience, explanation—from stated preferences or facts; only supplied fields change and PoB's overview refreshes.

Instructions

Change the player profile when the player asks or states a fact ("I'm playing SSF now", "I have 300 chaos", "explain less"). Only the given fields change. The league is checked against pathofexile.com. PoB's Overview header updates within seconds.

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": "profile_set"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalsNoReplace the goal list
leagueNoTrade league id (e.g. 'Standard', 'Hardcore'); empty string = current challenge league (its Hardcore version when hardcore)
currencyNoCurrency on hand (only given keys change)
hardcoreNotrue = Hardcore (a death moves the character to softcore): defences first, Hardcore trade league
playModeNotrade = buy upgrades; ssf = Solo Self-Found (no trading: craft/farm/drops); mixed = show both, labelled
add_goalsNo
experienceNopoe2 = knows PoE2, new to PoE1; new = new to Path of Exile; poe1 = experienced PoE1
remove_goalsNo
reset_learnedNoClear the learned topics so everything is explained again
explanationModeNoteach = explain each PoE1 mechanic once (compared with PoE2); concise = actions + numbers; deep = full mechanics and maths

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations the description carries the full burden, and it does disclose real traits: partial-merge semantics ("Only the given fields change"), external validation against pathofexile.com, and downstream propagation to PoB's Overview header. It omits failure behavior (what happens when a league id fails validation), whether reset_learned is destructive/irreversible, and any return contract.

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?

Four short sentences, front-loaded with the trigger condition, then merge semantics, then side effects. The final PoB sentence is slightly tangential but earns its place by telling the agent changes are visible quickly; there is no filler or repetition of the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter mutation tool with no annotations and no output schema, the description covers the trigger, update semantics, and side effects, but leaves out what the call returns and how errors surface. The reset_learned destructive flag is documented only in the schema, so the behavioral picture is incomplete.

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 80%, making 3 the baseline, and the description slightly exceeds it by illustrating how natural-language statements map onto fields — currency for "I have 300 chaos", playMode for "I'm playing SSF now", explanationMode for "explain less". It adds no detail on the interaction between league and hardcore or on the goal add/remove/replace trio.

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?

States a specific verb and resource ("Change the player profile") and makes the scope concrete with three quoted user utterances that map to distinct field groups. It does not name or contrast with siblings such as profile_get or set_build_notes, so an agent must infer the boundary from names alone.

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?

Gives an explicit trigger ("when the player asks or states a fact") backed by concrete examples like "I'm playing SSF now" and "explain less", which is clear positive guidance. It stops short of exclusions — nothing says when not to call it versus profile_get or set_build_notes.

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