Skip to main content
Glama

Skiddle

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).

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, providing a strong baseline. The description adds critical non-obvious behaviors: 60-day snapshot TTL, snapshots written only on cache miss (gaps mean no scan that day), and decay computed from daily closes not intraday. This exceeds annotation coverage and fully informs the agent.

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

Conciseness4/5

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

The description is a single dense paragraph but front-loads the key question and uses examples effectively. It earns its length by providing essential operational details, though it could be slightly more structured with bullet points or explicit sections to improve scanability.

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?

For a tool with two optional parameters, no enums, no nested objects, and no output schema, the description is exceptionally complete. It covers input defaults and constraints, output structure with all fields explained, data source behavior (cache-miss gaps, snapshot start dependency), and limitations (60-day TTL). No gaps remain for an agent to make informed decisions.

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

Parameters5/5

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

Schema coverage is 100% with descriptions for both parameters, but the description adds context-specific defaults (days default 14, max 30; window default '1wk') and explains their purpose within the tool's logic. Additionally, the description thoroughly documents all three output arrays (tracked, expired, snapshot_dates) with detailed field explanations, compensating for the lack of an output schema.

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 that the tool provides edge persistence and decay telemetry derived from daily polymarket_edges snapshots, using the specific question 'how long has this edge existed and is it shrinking?' as a concise purpose statement. It differentiates from the sibling tool polymarket_edges, which likely provides current snapshots, by focusing on historical time-series analysis.

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 implies when to use this tool by contrasting fresh edges with older ones ('a 3-week-old wide edge is wide for a reason'), but it does not explicitly state when not to use it or name alternatives. However, the context signals show sibling tools like polymarket_edges, and the description's focus on persistence suggests it is the next step after obtaining current edges.

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

All Skiddle 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

A3.9/5.0
Disambiguation3/5

Most tools have clearly distinct roles, but the ask_pipeworx / ask_pipeworx_beta / ask_pipeworx_grounded / deep_research cluster overlaps heavily as question-answering and research entry points, with ask_pipeworx_beta currently being an exact duplicate of ask_pipeworx. The prediction-market tools are individually differentiated but numerous enough that selecting the right one requires careful reading.

Naming Consistency4/5

The set is predominantly snake_case and mostly readable, with sensible prefixes like ask_, search_, polymarket_, and scan_. However, conventions mix verb-first names (remember, subscribe, validate_claim), noun-style names (categories, event, entity_profile), and adjective-noun names (recent_alerts, recent_changes), so the pattern is not fully uniform.

Tool Count2/5

34 tools is well above the 25-tool threshold where a server starts to feel heavy, and many could be consolidated (7+ prediction-market tools, 4+ overlapping ask/research tools, plus memory and subscription helpers). The breadth is somewhat justified by the Pipeworx data platform, but the surface is still overloaded for a single server.

Completeness4/5

For the broad data/research domain, coverage is strong: lookup, grounded verification, deep research, entity profiles, comparisons, change feeds, tool discovery, memory, and subscription lifecycle all have coherent coverage. Minor gaps exist, such as no explicit tool to read a pipeworx:// citation URI directly and a fairly thin Skiddle events side beyond search/detail/categories.

Resources