Skip to main content
Glama
Sign In
poe2-build-planner

poe2-build-planner

by cornndawwg
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Compare build options side by side

compare_builds
Read-only

Compares 2–4 full Path of Exile 2 build variants side by side to reveal damage, kill times, survivability, resistances, attribute gaps, and verdicts for clearing, bossing, and survival.

Instructions

Calculate 2–4 variants of a build the same way and compare them: e.g. two-handed vs one-handed + shield Titan, two ascendancies for the same theme, or a build with and without a key unique. Each variant is a full build (same fields as evaluate_build) with a label; usually they share most fields and differ in weapons, items, passives, skills or ascendancy. Returns damage, kill times, survival, life/ES, resistances, attribute shortfalls and verdicts per variant, the change against the first variant, and which is best for clearing, bossing and survival. Windows only for now.

Input Schema

NameRequiredDescriptionDefault
variantsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.7.0-beta
    • changedInput schema / properties / variants / items / required
      Previous value: -[
-  "label",
-  "class",
-  "level",
-  "passives",
-  "skills"
-]New value: +[
+  "class",
+  "level",
+  "passives",
+  "skills",
+  "label"
+]
  2. Changed1 schema field changedv0.6.0-beta
    • changedInput schema / properties / variants / items / properties / gearTier / description
      Previous value: -"Quality of the assumed rares: budget (default, mid rolls), mid (good rolls, more mods), high (perfect rolls, full mods)"New value: +"Quality of the assumed rares: budget (mid rolls), mid (good rolls, more mods), high (perfect rolls, full mods). Wins over goals.budget; without either, budget. goals.budget only raises end-game (65+) gear, so at campaign levels all three budgets look the same."
  3. First observedv0.5.0

TDQS

A4.3/5.0
Behavior4/5

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

With readOnlyHint=true already declared, the description stays consistent and adds real value: it discloses the returned metrics (damage, kill times, survival, life/ES, resistances, attribute shortfalls, verdicts), the delta against the first variant, and best-in-slot picks per activity. It also flags a hard platform constraint ('Windows only for now'), which is exactly the kind of context annotations cannot carry.

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?

Two sentences, front-loaded with the verb, the count limit and the comparison intent; the examples sit where an agent scanning for applicability will hit them. Dense but no filler, though the return-value enumeration and the examples together make it slightly long.

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

Completeness4/5

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

Covered end-to-end for a read-only analytical tool: variability scope, output contents, baseline-relative deltas, ranking dimensions and a platform caveat. With no output schema the return description matters and is supplied; with a deeply nested variant schema, the agent can rely on the schema for field-level detail.

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?

Top-level schema coverage is reported as 0% — the 'variants' array itself carries no description — so the description must compensate, and it does by stating the 2–4 count bound and that each entry is a full build with a label. It further explains the typical usage pattern (variants share most fields and differ in weapons, items, passives, skills or ascendancy), which meaningfully guides how to construct the array. Nested field semantics are left to the schema, which documents them well.

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 ('Calculate 2–4 variants of a build ... and compare them') plus the cardinality limit, and gives three concrete A/B scenarios (two-handed vs shield, two ascendancies, with/without a key unique). It also implicitly separates itself from evaluate_build by scoping single-build evaluation to the sibling.

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?

The examples make the use case unmistakable: you reach for this when choosing between options, not when evaluating one build. It also says each variant is 'a full build (same fields as evaluate_build)', which routes the agent to the sibling for the single-build case. There is no explicit 'do not use for X' statement, so it stops short of a 5.

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

Deploy Server

Other Tools