Skip to main content
Glama

Tcgdex

by io.github.pipeworx-io

Polymarket Edge Tracker

polymarket_edge_tracker
Read-onlyIdempotent

Edge persistence and decay telemetry built from daily polymarket_edges snapshots. Answers "how long has this edge existed and is it shrinking?" — a fresh wide edge and a 3-week-old wide edge are different trades (the latter is wide for a reason nobody is willing to take). Args: days (lookback, default 14, max 30), window (snapshot family, default "1wk"). RESPONSE: tracked[] = every opportunity in the LATEST snapshot with its full edge_pp_net time-series across prior snapshots, first_seen, trend (new | widening | stable | decaying) and decay_pp_per_day (both computed on |edge_pp_net| — the value itself is signed by trade direction, negative = SELL YES); expired[] = opportunities that appeared in earlier snapshots but are GONE from the latest (closed, resolved, or arbed away) with their lifespan_days — the median lifespan is your competition clock; snapshot_dates[] = which days actually have data (snapshots are written when polymarket_edges runs on a cache-miss, so gaps mean nobody scanned that day). LIMITS: history depth is bounded by the 60-day snapshot TTL and starts from when snapshotting was enabled; decay numbers come from daily closes of edge_pp_net (net of default slippage), not intraday.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
daysNoLookback in days (default 14, clamp 2-30).
windowNoWhich polymarket_edges window family to read snapshots for: 24hr | 1wk | 1mo (default 1wk).

TDQS

A4.1/5.0
Behavior5/5

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

The description adds rich behavioral context beyond annotations: explains it is read-only (consistent with readOnlyHint), describes data source (daily snapshots), response structure (tracked, expired, snapshot_dates), and limits (60-day TTL, decay from daily closes). No contradictions with annotations.

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

Conciseness3/5

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

Description is front-loaded with core question and structured with RESPONSE sections, but contains some redundancy (e.g., repeated explanation of decay computation). Could be more concise without losing clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given tool complexity (time-series analysis) and no output schema, the description thoroughly explains return fields (tracked[], expired[], snapshot_dates[]), their significance, and operational limits (data gaps, TTL). It leaves little ambiguity for an AI agent.

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

Parameters4/5

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

Schema coverage is 100% with descriptions for both parameters. Description adds value by explaining defaults ('days' default 14, 'window' default '1wk') and clarifying options ('max 30' though schema says clamp 2-30, minor inconsistency). Overall, it enhances understanding beyond schema alone.

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?

Description clearly states the tool's purpose: providing edge persistence and decay telemetry from daily Polymarket edges snapshots. It answers specific questions about edge duration and shrinking. The verb 'answers' and resource 'edge persistence and decay telemetry' are precise, and the tool distinguishes itself from siblings like 'polymarket_edges' and 'polymarket_arbitrage'.

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

Usage Guidelines2/5

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

No explicit guidance on when to vs. when not to use this tool. While the description implies usage for assessing edge age and decay, it does not mention alternatives or exclusion criteria. Given many sibling tools, this is a gap.

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

All Tcgdex toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation2/5

The four card tools are distinct, but the majority of the server is a Pipeworx/prediction-market platform with heavily overlapping entry points: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and discover_tools all serve similar query/discovery purposes, and ask_pipeworx_beta is explicitly an identical twin of ask_pipeworx. The six Polymarket tools and the ai_visibility/scan_competitor pair also have fuzzy boundaries that would make tool selection error-prone.

Naming Consistency2/5

All names are snake_case, but the pattern is highly inconsistent: some are verb_noun (get_card, search_cards, resolve_entity), some are bare verbs (remember, forget), some are noun-first (polymarket_edges, entity_profile, bet_research), and some are adjective_noun (recent_alerts, recent_changes). The ask_pipeworx variants share a name but differ only by suffix, which is not a clear action-oriented pattern.

Tool Count2/5

35 tools is squarely in the 'too many' territory, and the bloat is worse because the server is named Tcgdex while only 4 of 35 tools actually relate to trading cards. The remaining 31 tools form a sprawling multi-domain platform that mixes data queries, prediction markets, memory, subscriptions, AI visibility checks, and one-off utilities like generate_llms_txt and scan_dependency.

Completeness4/5

For the TCGdex card surface, the read-only workflows are covered well: search_cards leads to get_card, and list_sets leads to get_set, with no obvious dead ends. For the broader Pipeworx functionality, the set includes discovery, query, grounding, entity resolution, memory, subscriptions, and feedback, so the main workflows are supported—though the overall scope is sprawling rather than focused.

Resources