Skip to main content
Glama

Mediastack

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

A4.4/5.0
Behavior5/5

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

The description adds significant behavioral context beyond annotations: snapshot TTL (60 days), decay computation from daily closes (not intraday), response structure with detailed field meanings (trend values, decay_pp_per_day), and handling of gaps. Annotations already declare read-only, idempotent, and non-destructive, and the description fully aligns.

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 front-loaded with the core question and then breaks down the response into tracked, expired, and snapshot_dates. Although it is verbose, every sentence adds value, and the structure is logical. Minor reduction for length but not excessive.

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 the lack of output schema, the description fully explains the return structure, including all fields and their interpretations (trend values, decay_pp_per_day, lifespan_days, snapshot_dates). It also covers limitations (TTL, snapshot start, decay from closes). No gaps remain.

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

Parameters3/5

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

Schema coverage is 100%, so baseline is 3. The description repeats the default values and clamp of 'days' and mentions 'snapshot family' for 'window', but does not add new semantic meaning beyond what the schema already provides. No extra nuance or usage hints are given.

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's purpose: it provides edge persistence and decay telemetry. The verb 'track' is implicit in the title and description, and it explicitly answers a specific question about edge longevity. It distinguishes itself from sibling tools like 'polymarket_edges' by focusing on historical persistence and trend 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 the tool ('Answers how long has this edge existed and is it shrinking?') but does not explicitly state when not to use it or compare it to alternatives. The context is clear enough for an agent to infer usage, but lack of explicit exclusions prevents a perfect score.

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

All Mediastack 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

A4.1/5.0
Disambiguation5/5

Each tool has a detailed description clarifying its precise purpose, and even closely related tools (e.g., ask_pipeworx vs ask_pipeworx_grounded) are clearly differentiated by behavior and use case. No two tools appear to serve the same function.

Naming Consistency3/5

All names use snake_case, but the structural pattern is inconsistent: many follow verb_noun (compare_entities, resolve_entity), while others are noun-based (entity_profile, polymarket_arbitrage) or single verbs (subscribe, remember). This mix reduces predictability.

Tool Count3/5

With 32 tools, the server is quite large for an MCP server. While many tools are justified by the broad domain coverage, the high number can overwhelm agents and increase cognitive load, making it feel somewhat bloated.

Completeness4/5

The tool set covers a wide range of domains (company data, prediction markets, news, memory, subscriptions, etc.), and the generic ask_pipeworx and deep_research tools gateways to thousands of data sources, effectively filling gaps. However, some areas lack dedicated tools (e.g., weather, real estate) beyond the generic query.

Resources