Skip to main content
Glama

Blockchair

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?

Annotations already convey read-only, idempotent, and non-destructive behavior, so the bar is lower. The description adds substantial behavioral detail: return structure (tracked/expired/snapshot_dates), data caveats (snapshot misses, TTL limits, decay computed from daily closes not intraday), and the signed meaning of edge_pp_net. No contradictions 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?

The description is long but well-structured with Args, RESPONSE, and LIMITS sections. Every sentence provides substantive information, especially since there's no output schema. It front-loads the core purpose before diving into details, making it easy to scan.

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?

Given no output schema, the description excellently explains the return shape (tracked[] with fields, expired[] with lifespan_days, snapshot_dates[]) and critical caveats (snapshot TTL, gaps, daily closes). It covers not only return values but also the data source quirks, making it complete for the tool's complexity.

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 input schema already describes both `days` and `window` with 100% coverage, so baseline is 3. The description's args line adds minimal extra context (e.g., 'snapshot family' for window), but mostly restates defaults and bounds already present in the schema. It does not add significant format details beyond what the schema provides.

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 specific purpose: 'Edge persistence and decay telemetry built from daily polymarket_edges snapshots.' It explicitly answers a concrete question ('how long has this edge existed and is it shrinking?') and distinguishes itself from raw edge computation by referencing the sibling `polymarket_edges` tool, indicating this is a complementary analysis tool.

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: to analyze edge history and decay, contrasting fresh vs stale edges. It does not explicitly name alternatives or state when not to use it, but the use case is concretely framed ('fresh wide edge vs 3-week-old wide edge are different trades') and the response structure is outlined, aiding selection.

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

All Blockchair 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

B3.3/5.0
Disambiguation2/5

The major clusters are distinct (blockchain explorer, memory, subscriptions), but several tools have unclear boundaries: ask_pipeworx_beta is currently identical to ask_pipeworx, the three ask_pipeworx variants and deep_research all route questions, and the five Polymarket tools overlap heavily on edge detection. An agent would struggle to pick the right query tool or prediction-market tool without reading very long descriptions.

Naming Consistency2/5

Naming is a mix of single-word nouns (address, block, node, transaction, stats), verb-noun snake_case (validate_claim, generate_llms_txt), and noun-phrase snake_case (entity_profile, bet_research), with no consistent style or verb convention. There is no predictable pattern an agent can generalize from.

Tool Count2/5

36 tools is well above the comfortable range, and most are meta-tools for Pipeworx, Polymarket, memory, and subscriptions rather than Blockchair blockchain functionality. A large share of the count is redundant query and edge-analysis variants, so the size adds confusion rather than capability.

Completeness4/5

As a read-only research and monitoring gateway, the surface is fairly complete: universal routing, grounded answers, entity resolution, profiles, comparisons, claim validation, memory, and subscriptions all have lifecycle coverage. Relative to the Blockchair name, the blockchain side is thin but covers address, block, transaction, node, and stats, with only minor gaps like mempool or raw script details that agents can work around.

Resources