MTG Bench

semantic_card_search

Read-only

Vector search over card TEXT, for describing an effect that cannot be written as a filter: "cards that make a token when I attack", "punish opponents for drawing", "does what Rhystic Study does but cheaper". This is a query Scryfall syntax cannot express. Use search_cards instead for structured filters (color, type, mana value, set). Use find_synergies instead when the user names specific cards and wants partners for them. limit defaults to 10 and caps at 100 per call.

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": {
      "query": "<query>"
    },
    "name": "semantic_card_search"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No
`query`	Yes
`types`	No
`colors`	No
`format`	No
`manaValueMax`	No
`manaValueMin`	No

Output Schema

Name	Required	Description	Default
`results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedAug 9, 2026

TDQS

A4.4/5.0

Behavior5/5

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

The description adds meaningful behavioral context beyond the readOnlyHint annotation: it discloses that this is a vector search (not exact), that it handles natural language effect descriptions, and that limit defaults to 10 and caps at 100. This extra detail helps the agent set expectations and call the tool correctly.

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?

The description is compact and front-loaded with the purpose, followed by examples and alternatives. Every sentence adds value, including the limit behavior note. There is no wasted wording.

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?

The core purpose is well covered, but the presence of filter parameters (colors, types, mana value) contradicts the advice to use search_cards for structured filters, leaving an unresolved gap. Since an output schema exists, return values are not needed, but the param interaction should be clarified for full contextual completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It explains the `limit` parameter (default, cap) but says nothing about the other six parameters (types, colors, format, manaValueMin/Max). The claim 'Use search_cards instead for structured filters' even implies these parameters aren't meant for this tool, deepening the confusion about what they do.

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 the tool does vector search over card text for semantic effect descriptions, with concrete examples. It explicitly distinguishes itself from search_cards and find_synergies, making its unique purpose unmistakable.

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?

It gives explicit when-to-use guidance ('when an effect cannot be written as a filter') and names alternatives directly: 'Use search_cards instead for structured filters' and 'Use find_synergies instead when the user names specific cards.' This is exactly the kind of decision support an agent needs.

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

All MTG Bench tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?