shuffle_deckReshuffle a deck and reset all drawn cards back in. Returns updated remaining card count.
| Name | Required | Description | Default |
|---|---|---|---|
| deck_id | Yes | The deck ID to shuffle (e.g. "3p40paa87x90"). |
| Name | Required | Description | Default |
|---|---|---|---|
| deck_id | Yes | Unique identifier for the deck | |
| shuffled | Yes | Whether the deck was shuffled | |
| remaining | Yes | Number of cards remaining in the deck |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "deck_id": {
+ "description": "Unique identifier for the deck",
+ "type": "string"
+ },
+ "remaining": {
+ "description": "Number of cards remaining in the deck",
+ "type": "number"
+ },
+ "shuffled": {
+ "description": "Whether the deck was shuffled",
+ "type": "boolean"
+ }
+ },
+ "required": [
+ "deck_id",
+ "shuffled",
+ "remaining"
+ ],
+ "type": "object"
+}Input schema / examplesAdded value: +[
+ {
+ "deck_id": "3p40paa87x90"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description describes a mutation (reshuffling and resetting drawn cards), which contradicts the readOnlyHint=true annotation. This is a serious inconsistency, so the description scores 1 for behavioral transparency.
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 two concise sentences, front-loading the action and return value with no wasted words.
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?
The tool is simple with one parameter, and the description covers the action, the reset behavior, and the return value. The output schema exists, so return details are likely covered. The main gap is the annotation contradiction, but the description itself is complete for the tool's simple scope.
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 input schema already provides a complete description of the deck_id parameter (100% coverage), so the description adds no additional parameter semantics. Baseline 3 applies.
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's function: reshuffling a deck and resetting drawn cards. It uses a specific verb 'reshuffle' and specifies the resource (deck), distinguishing it from sibling tools like draw_cards and new_deck. The return count is also mentioned.
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 implies when to use the tool: when a deck needs to be reshuffled and its drawn cards returned. It provides clear context but does not explicitly name alternatives or state when not to use it, though the purpose makes this fairly obvious.
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.
Multiple tools have overlapping purposes: ask_pipeworx and ask_pipeworx_beta are functionally identical (beta just has experimental routing), and the Polymarket suite (bet_research, polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread) all revolve around prediction-market signal detection with unclear boundaries. Also ai_visibility_check and scan_competitor_ai_presence overlap heavily.
Naming is a mix of verb-first (draw_cards, resolve_entity, discover_tools) and noun-first (entity_profile, new_deck, recent_alerts) styles, with inconsistent prefixes (pipeworx_feedback vs ask_pipeworx) and no unifying convention. Some tools are bare verbs (recall, remember), others are noun phrases (polymarket_edges).
34 tools is excessive for a server named 'deckofcards' — only 3 tools relate to cards. Even as a general-purpose data/research server, 34 is on the high end and includes many near-duplicates (ask_pipeworx variants) and highly specialized tools that could be consolidated.
The research side is fairly complete (lookup, grounding, comparison, profiles, claim verification, memory, subscriptions), but the card-deck functionality is minimal (only create, draw, shuffle) and lacks any deck inspection or hand management. The server's scope is unclear, making it hard to assess true coverage.