Skip to main content
Glama
Path of Building MCP Server

Path of Building MCP Server

by urbanvcode

list_craftable_mods

List crafting bench mods an item class can take at a given item level, including what higher item levels unlock. Filter by prefix or suffix to find what fits an open slot.

Instructions

List the crafting bench mods an item class can take at a given item level, from Path of Building's ModMaster table. Use it to answer 'what can I put in the open suffix', and to say what a higher item level would unlock. A craft occupies a slot of its own type, so check the type of the affix being replaced, not only the one being added. LIMITS: bench crafts only, no essences, fossils or veiled mods, and no metacrafting. It does not know what the item already has, so pair it with classify_item_affixes.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "item_class": "<item_class>",
      "item_level": "<item_level>"
    },
    "name": "list_craftable_mods"
  }
}

Input Schema

NameRequiredDescriptionDefault
searchNoOptional wording, affix name, group or mod tag filter (e.g. 'Cold Resistance', 'life').
affix_typeNoRestrict to the slot type you actually have open.
item_classYesItem class as PoB names it: 'Body Armour', 'Helmet', 'Gloves', 'Boots', 'Shield', 'Ring', 'Amulet', 'Belt', 'Quiver', 'Wand', 'Bow', 'Staff', 'Sceptre', 'Dagger', 'Claw', 'One Handed Sword', and so on. A wrong value returns the full list of known classes.
item_levelYesThe item's item level. Crafts requiring a higher level are reported separately rather than hidden.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses data provenance, the mod-type scope limits, that higher-level crafts are reported separately rather than hidden, that a wrong item_class returns the known-class list, and that the tool is stateless about the item. It does not describe result volume, ordering, or grouping, which is the remaining gap.

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 purpose, then usage, then a clearly marked LIMITS block, then the sibling pointer — good structure with no filler. Slight overlap between the 'open suffix' example and the affix_type guidance keeps it from being maximally tight.

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 four-parameter, read-only static-data lookup with no annotations and no output schema, the description covers what the tool answers, what it excludes, how item_level affects results, and which tool to combine it with. Nothing an agent needs in order to select and call it correctly is missing.

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?

Schema description coverage is 100%, so all four parameters are already documented, including the enum and the wrong-value fallback for item_class. The description adds only modest meaning beyond that — clarifying that affix_type should match the slot of the affix being replaced — so the baseline of 3 applies.

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 and resource — 'List the crafting bench mods an item class can take at a given item level' — and names the data source (PoB's ModMaster table). It is immediately distinguishable from siblings like find_affix_tiers or classify_item_affixes, which concern affix tiers and item inspection rather than bench craft availability.

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?

Gives concrete use cases ('what can I put in the open suffix', 'what a higher item level would unlock'), explicit exclusions (no essences, fossils, veiled mods, no metacrafting), and names the sibling to pair with (classify_item_affixes) along with the reason it is needed. The warning to check the slot type of the affix being replaced is a real when-to-use constraint.

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