Skip to main content
Glama
Cladios34

mtg-mcp-server

by Cladios34

simulate_opening_hands

Read-onlyIdempotent

Simulate Commander opening hands and mulligans via Monte Carlo to estimate keep rates, land distribution, and early mana curve.

Instructions

Monte Carlo simulation of opening hands, mulligans, and early mana curve.

Simulates Commander-free-mulligan opening hands and a greedy 5-turn goldfish to estimate keep rates, kept-hand land distribution, and spendable mana per turn. Exclude the commander from decklist: it simulates a 99-card Commander library.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
seedNoRNG seed for reproducible results (omit for random)
decklistYesCard entries, excluding the commander (a 99-card Commander library)
keep_ruleNoKeep rule: 'playability' (3-turn goldfish of the hand: development, flood, gas) or 'lands_v1' (legacy effective-land range only)playability
max_landsNoMaximum effective land cards in a kept hand (flood check, MDFC count 0.5)
min_landsNoKeep threshold: minimum turn-3 developed mana (playability rule) or minimum effective lands (lands_v1 rule)
iterationsNoNumber of simulated games (100-100000)
tutor_awareNoDetect tutors, count cheap ones as gas, and report per-tutor targets plus the odds of an opening hand holding a tutor
exclude_cardsNoCard names to force-classify as non-mana
free_mulliganNoCommander free mulligan: the first mulligan redraws 7 cards without bottoming
commander_colorsNoCommander color identity (e.g. 'mardu', 'WBR', 'boros') to enable the playability-rule color screen: hands that cannot source every color are mulliganed
count_mdfc_landsNoCount modal-double-faced land backs as half a land
gas_cmc_thresholdNoA hand needs at least one non-source card at or below this mana value to be kept (playability rule)
extra_mana_sourcesNoCard names to force-classify as mana rocks
Behavior4/5

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

Annotations (readOnlyHint, openWorldHint, idempotentHint) indicate safe, read-only behavior. The description adds behavioral context: it simulates, uses Monte Carlo, performs a 5-turn goldfish, and excludes the commander. This goes beyond annotations, though it does not mention performance considerations or the probabilistic nature.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short paragraphs front-loading the core purpose and key details. Every sentence adds value; there is no fluff or repetition.

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?

The description covers the simulation's purpose, inputs, and high-level outputs (keep rates, land distribution, spendable mana). Despite 13 parameters and no output schema, it gives a reasonable understanding of what to expect, though the exact return format is not specified.

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 coverage is 100%, so all parameters have descriptions. The description's main param-related addition is restating 'exclude the commander', which is already in the schema. No extra meaning beyond what the schema provides.

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 clearly states it is a Monte Carlo simulation of opening hands, mulligans, and early mana curve. It specifies what it simulates (Commander free mulligan, keep rates, land distribution, spendable mana) and that the commander is excluded. This is specific and distinguishes it from siblings like hand_probability.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains what the tool does but does not explicitly state when to use it versus alternatives like 'hand_probability' or 'deck_analysis'. It implies Commander usage but lacks explicit guidance on when not to use it.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Cladios34/mtg-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server