Skip to main content
Glama

Ensembl

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

A4.5/5.0
Behavior5/5

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

The description provides rich behavioral context beyond the readOnlyHint and idempotentHint annotations: snapshot TTL, cache-miss write behavior, data gaps, computation of decay from daily closes, and the sign convention for edge_pp_net. It also explains the limitation of history depth and snapshot start time. No contradiction with annotations; it enhances them.

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 labeled sections (Args, RESPONSE, LIMITS) and front-loaded purpose. Despite being fairly long, every sentence adds essential information about behavior, response fields, or limitations. No fluff or redundant content.

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?

With no output schema, the description thoroughly explains the response structure (tracked[], expired[], snapshot_dates[]) and key fields (trend, decay_pp_per_day, lifespan_days). It also covers edge cases like data gaps, snapshot TTL, and computation methodology. The tool's complexity is fully addressed.

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?

The schema already covers both parameters with clear descriptions (days lookback with default and clamp, window family with options). The description adds 'lookback' and 'snapshot family' semantics, which is marginal reinforcement, and even introduces a slightly contradictory 'max 30' vs schema's 'clamp 2-30'. With 100% schema coverage, the baseline of 3 is appropriate; the description does not significantly compensate.

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 defines the tool as edge persistence and decay telemetry built from daily polymarket_edges snapshots, answering a specific question about edge age and shrinkage. It distinguishes itself from the sibling polymarket_edges by focusing on historical persistence and decay rather than current edges. The purpose is specific and unambiguous.

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 the tool is for analyzing edge history and decay, contrasting a fresh edge with an old one to justify its utility. It does not explicitly name sibling tools or state when not to use it, but the context of snapshots and the competition clock strongly implies the intended use case. Clear context without formal exclusions.

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

All Ensembl 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

A3.6/5.0
Disambiguation2/5

Multiple tool families heavily overlap: ask_pipeworx, ask_pipeworx_beta (explicitly identical), ask_pipeworx_grounded, deep_research, and validate_claim all answer natural-language questions, while polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread, and bet_research all analyze prediction markets. An agent would struggle to pick the correct tool without reading very long descriptions.

Naming Consistency3/5

All names are snake_case and readable, but the style is inconsistent: some are bare nouns (sequence, variation, homology), some are single verbs (lookup, recall, forget), and others are long descriptive phrases (scan_competitor_ai_presence, polymarket_kalshi_spread). There is no consistent verb_noun or resource_noun pattern across the set.

Tool Count2/5

38 tools is excessive for a coherent server, and nearly all of them are unrelated to the server's stated name ('Ensembl') — only about 7 tools (lookup, lookup_symbol, sequence, variation, vep, xrefs, homology) actually belong to the Ensembl domain. The rest form several unrelated clusters (Pipeworx data queries, prediction markets, memory, subscriptions), making the tool count feel bloated and unfocused.

Completeness2/5

For an Ensembl server, the surface is thin: it covers ID lookup, sequence retrieval, variants, VEP, xrefs, and homology, but omits other core Ensembl functionality such as gene trees, alignments, regulation, expression, and assembly data. Meanwhile the many non-Ensembl tools don't form a complete domain of their own — they are a grab bag of unrelated utilities.

Resources