Skip to main content
Glama

Madrid Events

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).

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses crucial behavioral details: the response structure (tracked[], expired[], snapshot_dates[]), the sign convention for edge_pp_net (negative = SELL YES), the computation basis (daily closes, net of default slippage), and the storage limits (60-day TTL, snapshot enabled time). This greatly exceeds what annotations alone convey.

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 dense but well-organized: a lead question, then a RESPONSE section enumerating output fields, and a LIMITS section. Every sentence adds value, with no filler. The structure makes the long description easy to parse.

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?

Since there is no output schema, the description fully explains the return values: tracked[] with time-series, trend, and decay metrics; expired[] with lifespan; and snapshot_dates[] with gap semantics. It also covers data freshness and historical limits. For a telemetry tool with 2 optional params, this is complete.

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% with both parameters described in the input schema. The description mostly repeats the defaults and window families ('days ... default 14, max 30', 'window ... default 1wk') without adding new semantic meaning. It does not explain how parameters interact with response data beyond mentioning lookback, so it meets the baseline but adds little extra.

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 opens with a clear, specific purpose: 'Edge persistence and decay telemetry built from daily polymarket_edges snapshots' and poses the exact question it answers: 'how long has this edge existed and is it shrinking?'. This distinguishes it from sibling tools like polymarket_edges by focusing on time-series decay rather than current edge values.

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 provides strong contextual guidance through the distinction between 'a fresh wide edge and a 3-week-old wide edge' being 'different trades', implying this should be used when edge age or decay matters. It also clarifies snapshot gaps via cache-miss behavior. However, it does not explicitly name sibling alternatives or state 'use X when Y'.

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

All Madrid Events 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

The set contains several heavily overlapping clusters: three ask_pipeworx variants (with ask_pipeworx_beta explicitly identical to ask_pipeworx right now) and six polymarket-related tools that all orbit edge detection, arbitrage, and fill risk. An agent choosing among bet_research, polymarket_edges, polymarket_arbitrage, and polymarket_kalshi_spread would have a hard time picking the right one.

Naming Consistency3/5

Most tools use readable snake_case, so the naming is not chaotic. However, the pattern is mixed: some are verb_noun (compare_entities, resolve_entity), some are brand-style (ask_pipeworx, ask_pipeworx_beta), and some are noun-only phrases (events, polymarket_arbitrage, pipeworx_trending). It is consistent in casing but not in structural convention.

Tool Count2/5

32 tools is well beyond the usual well-scoped range, and the count is inflated by multiple near-duplicate clusters for querying, prediction markets, and memory/subscription utilities. For a server named Madrid Events, this is especially disproportionate since only one tool actually relates to Madrid events.

Completeness2/5

Relative to the Madrid Events name, the domain coverage is almost entirely missing: only events addresses the stated purpose, and it is read-only with no detail view, booking, or management operations. If interpreted as the broader Pipeworx platform, coverage is richer, but the server's stated identity makes the gap severe.

Resources