Skip to main content
Glama

Crystallography

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?

The description adds significant context beyond the annotations (readOnlyHint, idempotentHint, etc.) by explaining data gaps (cache-miss), decay calculation (daily closes, not intraday), and snapshot origin. 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.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is information-dense but uses mixed formats (sentence fragments, parentheticals, all-caps sections). It could be better structured with bullet points or clearer separates for response fields, but it remains functional.

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?

Despite no output schema, the description fully details the response structure (tracked[], expired[], snapshot_dates[]) with field meanings and limitations. It covers all necessary context for an agent to interpret results 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% (both parameters documented). The description reinforces defaults and adds functional context (e.g., 'window' as 'snapshot family'). It slightly exceeds the baseline by clarifying the meaning of the parameters.

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 providing 'Edge persistence and decay telemetry' from daily snapshots, answering a specific question about edge age and shrinkage. It distinguishes itself from siblings like 'polymarket_edges' (which likely provides current edge data) by focusing on time-series behavior.

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 implicitly guides usage by contrasting fresh vs. aged edges, and explicitly notes limitations (TTL, snapshot timing). It does not explicitly list alternatives or when to avoid, but the context is sufficient for an agent to decide.

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

All Crystallography 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

A3.7/5.0
Disambiguation2/5

There are three overlapping ask_pipeworx variants (stable, beta, grounded) plus a dense cluster of six polymarket trading/arbitrage tools, making misselection likely. Several other tools also blur together around research aggregation and entity lookup (entity_profile, compare_entities, recent_changes, validate_claim).

Naming Consistency3/5

All tool names are lowercase and snake_case, but the pattern is inconsistent: some are verb_noun (get_structure, resolve_entity), some are noun phrases (recent_changes, polymarket_edges), and a few are bare verbs (remember, forget, recall). The ask_pipeworx_beta/ask_pipeworx_grounded suffix pattern is readable but not mirrored across the rest of the set.

Tool Count2/5

34 tools is above the 25+ threshold for a server whose stated purpose is Crystallography, and only 3 of those tools actually serve that domain. The rest belong to Pipeworx data lookup, Polymarket betting, memory, research, subscriptions, and unrelated utilities, so the count feels excessive and the scope is unclear.

Completeness3/5

As a broad data-research toolset, there is decent lifecycle coverage: lookup, research, grounded verification, entity resolution, comparison, subscriptions, feedback, and memory all exist. However, for a server named Crystallography the domain surface is thin (search/get/get CIF only), and there is no general web-search fallback for topics not in the structured catalog.

Resources