Skip to main content
Glama

Crontab

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

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds significant behavioral context beyond this: the 60-day snapshot TTL bound, that snapshots are only written on cache-miss (so gaps mean no scan), and that decay numbers come from daily closes of edge_pp_net (net of slippage), not intraday. It also explains response structure in detail. No contradiction with annotations.

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?

Though long, the description is well-structured into explicit sections (Args, RESPONSE, LIMITS). Every sentence carries substantive information: purpose, usage context, parameter meaning, response fields, and limitations. No fluff or repetition of annotations. The density is appropriate for the tool's complexity.

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?

The tool is complex (time-series telemetry, trend classification, expired opportunities), yet the description covers all key aspects: how data is derived, what each response field means (including trend enum values), what limitations exist (TTL, cache-miss gaps), and how parameters affect the query. With no output schema and only 2 params, this description is complete enough for an agent to select and invoke correctly.

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%, and the schema descriptions already cover defaults and ranges. The description adds value by connecting parameters to their conceptual role: 'window (snapshot family)' clarifies that the parameter selects which polymarket_edges snapshot family to read, and the note about lookback depth being bounded by TTL gives purpose to 'days'. This pushes above the baseline 3.

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 'Edge persistence and decay telemetry built from daily polymarket_edges snapshots' and explicitly states the core question it answers: 'how long has this edge existed and is it shrinking?' This clearly specifies the tool's verb (track/measure), resource (polymarket_edges snapshots), and distinguishes it from sibling tools like polymarket_edges by focusing on historical persistence and 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 clear context for when to use the tool: it answers the persistence/decay question and explains why the distinction matters ('a fresh wide edge and a 3-week-old wide edge are different trades'). It does not explicitly name sibling alternatives or state 'use this instead of X', but the intent is unambiguous. The lack of explicit exclusions keeps it from a 5.

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

All Crontab 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

Several tool clusters have blurred boundaries: ask_pipeworx_beta explicitly states it currently matches ask_pipeworx exactly, making them indistinguishable, and the five Polymarket tools (polymarket_edges, polymarket_arbitrage, polymarket_fill_risk, bet_research, polymarket_kalshi_spread) all target prediction-market opportunities with overlapping concerns. The meta-tools (discover_tools, suggest_questions, pipeworx_trending) and entity tools (entity_profile, compare_entities, recent_changes) are better separated by their descriptions, but the identical beta/stable pair alone forces a low score.

Naming Consistency3/5

All tool names use snake_case, but the naming conventions are mixed: some follow verb_noun (describe_cron, next_runs, validate_claim), some are bare verbs (remember, recall, forget), and many are brand-prefixed noun phrases (ask_pipeworx, pipeworx_trending, polymarket_edges, bet_research). The pattern is readable and mostly predictable by prefix/domain, but there is no single consistent convention across the set.

Tool Count2/5

33 tools is above the reasonable threshold for a focused server, and the count is especially disproportionate for a server named 'Crontab': only 2 tools (describe_cron, next_runs) actually deal with cron, while roughly 24 tools are Pipeworx data-query, prediction-market, and memory utilities unrelated to the server's apparent purpose. The bulk of the tool surface feels like it belongs on a different server, making the count mismatched with the stated scope.

Completeness2/5

For a cron-focused server, the surface is incomplete: it can describe cron expressions and compute next runs, but has no tool to create, update, or delete a scheduled cron job — subscribe/unsubscribe manage data-event subscriptions, not cron schedules. The Pipeworx data side is broad (lookup, grounded verification, entity profiles, comparisons, research), but that completeness belongs to a different domain and does not rescue the cron purpose implied by the server name.

Resources