Skip to main content
Glama

npm

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

A4.7/5.0
Behavior5/5

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

Adds substantial behavioral detail beyond annotations: 60-day snapshot TTL, history starts when snapshotting was enabled, snapshots written only on cache-miss (gaps = no scan), decay computed from daily closes not intraday, and signed edge_pp_net (negative = SELL YES). Annotations are readOnly/openWorld/idempotent and the description complements them without contradiction.

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 long, but every paragraph earns its place: purpose, args, response fields with meanings, and limitations are clearly sectioned (Args, RESPONSE, LIMITS). Front-loaded with the core purpose, no filler, and the structure improves scannability without losing precision.

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 read-only telemetry tool with no output schema, the description fully explains the return structures (tracked, expired, snapshot_dates), their semantics, and edge cases like gaps, TTL, and sign conventions. Parameter coverage is complete via schema, making the tool ready for correct invocation and result interpretation.

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%, so baseline is 3. The description goes beyond the schema by introducing 'snapshot family' semantics for window and clarifying days as lookback with a max of 30. It also ties window into the RESPONSE structure, adding context the schema alone does not provide.

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?

States specific verb+resource: 'Edge persistence and decay telemetry' and answers the concrete question 'how long has this edge existed and is it shrinking?'. Clearly distinguishes from sibling 'polymarket_edges' by focusing on time-series persistence rather than current edge detection.

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?

Implies when to use via the example that a fresh wide edge and a 3-week-old wide edge are different trades, and mentions the 'competition clock' of median lifespan. However, it does not explicitly name alternatives or exclusion criteria, though the niche is clear from the purpose and the sibling list.

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

All npm 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

A3.8/5.0
Disambiguation4/5

Descriptions are exceptionally detailed and differentiate tools well; the ask_pipeworx family (stable/beta/grounded), polymarket tools, and npm lookup tools each have clear separation of intent. Minor overlap exists between polymarket_edges and polymarket_arbitrage (both surface opportunities) and between discover_tools, suggest_questions, and pipeworx_trending (all aid discovery), but descriptions mostly resolve the ambiguity.

Naming Consistency3/5

All names are snake_case and several families are consistent (get_*, list_*, search_*, ask_pipeworx, polymarket_*), but the convention is inconsistent: verb-first names (resolve_entity, validate_claim, scan_dependency) coexist with noun-first or noun-only names (entity_profile, deep_research, bet_research, recent_alerts, ai_visibility_check, pipeworx_trending, polymarket_arbitrage). No clear governing pattern beyond snake_case.

Tool Count2/5

36 tools is well over the 25-tool heavy threshold, and the majority (~29) are unrelated to the server's declared 'npm' identity — they are Pipeworx data-query, prediction-market, memory, and subscription tools. Only about 7 tools (search_packages, get_package, get_version_info, list_versions, get_downloads, scan_dependency, generate_llms_txt) actually pertain to npm. The scope is a kitchen-sink mismatch with the server name.

Completeness3/5

For npm, the read-side surface is reasonably complete: search, inspect package metadata, version listings, download counts, and a dependency-safety composite check. However, there are no lifecycle operations (publish, unpublish, deprecate, set versions/tags), leaving a notable gap, and the bulk of the server's functionality (data queries, prediction bets) belongs to an entirely different domain that can't be cohesively evaluated against the npm purpose.

Resources