random_cardGet a random Magic: The Gathering (MTG) card, optionally filtered by a Scryfall query (e.g. "is:commander", "c:blue").
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Optional Scryfall filter query. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "query": "is:commander"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering safety and idempotency. The description adds value by explaining the filtering capability and Scryfall query syntax, but does not disclose additional behavioral traits beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no wasted words. Essential information is front-loaded: what the tool does and how to filter. Perfectly structured for quick parsing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given only one optional parameter and no output schema, the description sufficiently covers the tool's purpose and filtering. It could optionally describe the return format but is still complete for a simple random retrieval tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'query' is described in the schema with 100% coverage. The description goes beyond by providing concrete examples ('is:commander', 'c:blue'), which clarifies the query format and adds meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves a random MTG card with optional Scryfall query filtering. The verb 'get' and resource 'random card' are specific, and it distinguishes from sibling tools like get_card (specific card) and search_cards (list).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives example filter queries but does not explicitly state when to use this tool versus alternatives like search_cards. Usage is implied through context but lacks explicit guidance or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have distinct purposes, but the ask_pipeworx family (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded) plus deep_research creates real boundary confusion, and the six polymarket_* tools overlap enough to require careful reading. The few Scryfall card tools are clearly distinct from the Pipeworx bulk, but the name mismatch adds selection friction.
All tool names use snake_case and most follow a verb_noun pattern (get_card, search_cards, resolve_entity, validate_claim). There are deviations like entity_profile, deep_research, and pipeworx_trending, but the nested families (ask_pipeworx*, polymarket_*) are internally consistent and predictable.
35 tools is above the 25+ threshold and is especially mismatched with the server name 'Scryfall', which implies a focused MTG card server. Only 4 of 35 tools relate to Scryfall; the remaining 31 form a sprawling data-research platform that would be more appropriately split into separate servers.
The dominant Pipeworx data-research surface is remarkably complete: universal lookup, grounded answers, deep research, entity profiles, comparisons, entity resolution, claim validation, change feeds, subscriptions, memory, and discovery. The Scryfall subset covers core card lookup (search, get by name, random, list sets) but lacks rulings, set details, and card-by-ID lookups, which is a minor gap relative to the server's stated name.