Skip to main content
Glama

Performance Review

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. Added
  2. Removed
  3. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive. Description adds rich behavioral details: output structure, trend computation, decay formula, snapshot TTL, and data gaps. No contradiction.

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?

Description is dense with information but somewhat lengthy; could benefit from clearer structure. However, every sentence adds value, no fluff.

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 lack of output schema, description fully explains output (tracked[], expired[], snapshot_dates[]) and covers limitations, edge cases, and computational details. Complete for the tool's complexity.

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 provides parameter descriptions (100% coverage). Description adds value by specifying defaults (14, '1wk'), clamp (2-30), and effect of parameters, going beyond the 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?

Description clearly states the tool's purpose: edge persistence and decay telemetry. It answers specific questions ('how long has this edge existed and is it shrinking?') and distinguishes from siblings like polymarket_edges and bet_research.

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?

Description explains when to use (for checking edge persistence and decay) and implies when not (e.g., for non-persistent edge data). Does not explicitly list alternatives but mentions snapshot families and limits.

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

All Performance Review 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

Several tools occupy adjacent territory: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all answer questions with only subtle differences in grounding and breadth, and discover_tools overlaps with suggest_questions. The prediction-market tools (polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread, bet_research) each have distinct mechanics but a less careful agent could easily misfire between them.

Naming Consistency3/5

Most tools follow a verb_noun pattern (ask_pipeworx, compare_entities, generate_llms_txt, list_subscriptions), but there are notable exceptions: performance_review_generate reverses the order, entity_profile is noun_noun, and recall/remember/forget are bare verbs. The pipeworx_ and polymarket_ prefixes help group families, but the mixed styles prevent a higher score.

Tool Count2/5

At 32 tools this is a heavy surface for one MCP server, exceeding the 25+ threshold where agents struggle to discover and choose among options. The breadth is understandable given the many subdomains (data lookups, prediction markets, memory, subscriptions, feedback), but the count still feels like tool sprawl rather than a tightly scoped set.

Completeness4/5

As a data/research/prediction-market platform the surface is remarkably complete: query, grounded verification, deep research, entity resolution, comparisons, claim validation, visibility audits, subscriptions, memory, and feedback loops are all covered. Minor gaps exist—there is no direct tool for bulk exports or for editing subscriptions, and some meta-tools duplicate discovery—but agents can accomplish the core workflows without dead ends.

Resources