Skip to main content
Glama

MTG Tools — Commander deck review and mana bases

Find a targeted card replacement

find_replacements
Read-only

Suggest at most one replacement for a named card in a Commander deck. Accepts deck text or a supported public deck URL and checks budget, legality, ownership, protected cards, and exclusions.

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": {
      "deck": "<deck>",
      "replaceCard": "<replaceCard>",
      "commander": "<commander>"
    },
    "name": "find_replacements"
  }
}

Input Schema

NameRequiredDescriptionDefault
deckYesFull quantity-prefixed decklist, or a public HTTPS Moxfield/Archidekt deck URL without query parameters.
ownedNoQuantity-prefixed owned cards, up to 150 card entries and 16000 characters. Split larger collections before analysis.
lockedNo
qaTestNoInternal QA only: set true when the user explicitly says this is our test run. Excludes the call from usage/revenue statistics. Omit for normal player requests.
bracketNo
excludedNo
budgetUsdNo
commanderYes
maxChangesNo
replaceCardYes
searchContextNoOptional opaque context from a preceding card search for attributing a related request.
collectionModeNocollection_only uses only available owned cards; collection_first prioritizes owned cards then purchases within budget. In collection modes, owned is total inventory including this deck; copies in this deck are reserved. One deck at a time, up to 150 entries. No safe swaps may be found.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / searchContext / description
      Previous value: -"Return the opaque searchContext from the preceding card search when the user requests a follow-up. Never invent it or run follow-ups automatically."New value: +"Optional opaque context from a preceding card search for attributing a related request."
  2. Changed1 schema field changed
    • addedInput schema / properties / searchContext
      Added value: +{
      +  "description": "Return the opaque searchContext from the preceding card search when the user requests a follow-up. Never invent it or run follow-ups automatically.",
      +  "maxLength": 400,
      +  "type": "string"
      +}
  3. Changed1 schema field changed
    • addedInput schema / properties / collectionMode
      Added value: +{
      +  "description": "collection_only uses only available owned cards; collection_first prioritizes owned cards then purchases within budget. In collection modes, owned is total inventory including this deck; copies in this deck are reserved. One deck at a time, up to 150 entries. No safe swaps may be found.",
      +  "enum": [
      +    "standard",
      +    "collection_only",
      +    "collection_first"
      +  ],
      +  "type": "string"
      +}
  4. Changed1 schema field changed
    • addedInput schema / properties / qaTest
      Added value: +{
      +  "const": true,
      +  "description": "Internal QA only: set true when the user explicitly says this is our test run. Excludes the call from usage/revenue statistics. Omit for normal player requests.",
      +  "type": "boolean"
      +}
  5. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare read-only, open-world, non-destructive behavior; the description adds that the tool checks budget, legality, ownership, protected cards, and exclusions and returns at most one suggestion. It still omits failure modes and does not reconcile 'at most one replacement' with the maxChanges parameter.

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 sentences, front-loaded with the action and scope, with no filler. The second sentence efficiently lists accepted inputs and constraint checks.

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 12-parameter tool with no output schema, the definition covers the core flow and constraint checks but not the return shape, failure cases, or several parameters. Annotations and schema descriptions fill some gaps, but the description is thinner than the tool's complexity warrants.

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?

With only 42% schema coverage across 12 parameters, the description helps by naming several checks that map to budgetUsd, bracket, owned/collectionMode, locked, and excluded. However it leaves maxChanges, qaTest, searchContext, and the required commander parameter unexplained, and 'at most one replacement' conflicts with maxChanges allowing up to 15.

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, 'Suggest', and resource, 'replacement for a named card', scoped to a Commander deck. The core action is clear, though it does not explicitly distinguish itself from sibling deck-improvement tools such as repair_deck or upgrade_precon.

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 implies when to use the tool by describing the targeted replacement scenario and accepted deck inputs, but it gives no explicit when-to-use/when-not guidance or named alternatives. An agent can infer the scenario but must still choose among siblings without help.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources