Skip to main content
Glama

Mempool Space

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

A4.7/5.0
Behavior5/5

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

Annotations declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, which the description complements by explaining snapshot-based data, response structure (tracked, expired, snapshot_dates), and limits (60-day TTL, start time). No contradictions. Adds rich behavioral context 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.

Conciseness5/5

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

The description is well-structured with headers (ARGS, RESPONSE, LIMITS), front-loads the core question, and every sentence adds value. Despite length, it is concise and informative.

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?

The description thoroughly explains the output fields (tracked with trend, decay, etc.; expired with lifespan; snapshot_dates) and constraints. No output schema is present, but the description compensates fully. Annotations cover safety. The tool is complex, but the description leaves no critical gaps.

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%, and the description adds defaults (days=14, window='1wk'), constraints (max 30, clamped 2-30), and context (snapshot family). This enhances understanding beyond the schema descriptions.

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 provides edge persistence and decay telemetry from daily snapshots, answering 'how long has this edge existed and is it shrinking?'. It is distinct from sibling tools like polymarket_edges (likely real-time edges) and other Polymarket tools. The verb 'track' aligns with the name and outcome.

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

Usage Guidelines4/5

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

The description explains the use case: distinguishing between fresh wide edges and old wide edges. It implicitly contrasts with real-time edge data (available via polymarket_edges). However, it does not explicitly state when not to use or name alternatives, leaving some ambiguity.

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

All Mempool Space 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

B3.1/5.0
Disambiguation2/5

The set mixes two unrelated domains — Bitcoin mempool explorer tools and the much larger Pipeworx data-query platform — and within the Pipeworx half several tools route to the same 5,743-tool catalog (ask_pipeworx, deep_research, discover_tools, suggest_questions). ask_pipeworx_beta is currently an exact behavioral duplicate of ask_pipeworx, and the polymarket_* family has fuzzy boundaries (arbitrage vs edges vs fill_risk, with fill-checking living in both polymarket_arbitrage and polymarket_fill_risk), so an agent must read long descriptions to avoid misselection.

Naming Consistency3/5

All names use snake_case and there are recognizable sub-families (get_* Bitcoin lookups, ask_pipeworx_*, polymarket_*), but conventions are mixed across the whole set: bare-noun state tools (block_height, hashrate, mempool_stats, mining_pools) sit beside verb_noun actions (get_block, list_subscriptions), and prefix placement is inconsistent (ask_pipeworx vs pipeworx_trending/pipeworx_feedback). The naming is readable but not predictable enough to guess a tool's name from its function.

Tool Count2/5

41 tools is well past the 25+ threshold for a coherent server, and the count is inflated by bundling two unrelated products under a server named after only the smaller half (~10 Bitcoin tools vs ~31 Pipeworx tools). Many Pipeworx tools are convenience wrappers around one universal router, adding surface area without adding genuinely new capabilities.

Completeness3/5

Each half is internally workable: the Bitcoin side covers blocks, transactions, addresses, fees, hashrate, and pools, while the Pipeworx side provides broad query, research, subscription, and memory lifecycles. However, there are notable gaps relative to each domain (no block-list/fee-history endpoints on the explorer side; no direct per-source CRUD on the data side), and no single coherent domain is fully served because the server's stated identity matches only a fraction of its tools.

Resources