Skip to main content
Glama

Always Seven

by io.github.pipeworx-io

Polymarket Fill Risk

polymarket_fill_risk
Read-onlyIdempotent

Realizable-vs-theoretical edge check against live CLOB order-book depth. REQUIRES one of market (single-market mode) or event (basket/partition mode). SINGLE-MARKET: pass a market slug/URL + side (buy_yes|sell_yes|buy_no|sell_no, default buy_yes) + size_usd (default 1000 — max spend on buys, target proceeds on sells); walks the ladder and returns top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, and a verdict (clean|degraded|cannot_fill). BASKET: pass an event slug/URL + side (sell_yes = capture overround by selling every leg, buy_yes = capture underround; default auto from partition sum) + size_usd interpreted as settlement notional S (shares per leg; each share pays $1); returns theoretical_sum vs realizable_sum (top-of-book vs VWAP across all legs), capture_ratio, profit_usd at executed size, per-leg fill detail, thin_legs[], max_clean_notional_usd, and forced_directional_risk naming the legs most likely to strand you unhedged. USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500 — theoretical overround on thin books is not capturable, and partial basket fills convert an arb into an unhedged directional position (the dominant loss mode in real arb-bot P&L).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sideNoSingle-market: buy_yes | sell_yes | buy_no | sell_no (default buy_yes). Basket: sell_yes | buy_yes (default auto — sell if partition sum > 1, buy if < 1).
eventNoBasket mode: event slug or full polymarket.com URL — checks every leg of the partition.
marketNoSingle-market mode: market slug or full polymarket.com URL.
size_usdNoSingle-market: USD to spend (buys) or target proceeds (sells). Basket: settlement notional — shares per leg, each paying $1 at resolution. Default 1000, clamp 10–1,000,000.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added
  2. Removed
  3. Added

TDQS

A4.9/5.0
Behavior5/5

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

Annotations indicate readOnly=true, idempotent=true, no destructive effect. Description confirms it is a check, details the process (walks ladder, returns verdict) and warns of forced directional risk. No contradiction, and adds rich behavioral context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

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

Description is dense and informative, properly front-loaded with purpose. While each sentence is justified, the length could be slightly reduced without losing clarity. Still, structure is logical with clear mode separation.

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?

Without an output schema, the description effectively lists all return fields (top_of_book, vwap_fill_price, slippage_pp, verdict, etc.) and explains edge cases (thin legs, forced directional risk). Covers all necessary context for correct tool usage and interpretation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but description adds significant context: explains 'market' is single-market mode, 'event' is basket mode, clarifies meaning of 'size_usd' for buys vs sells and basket vs single-market, and provides defaults and clamps. Greatly aids correct parameter usage.

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?

Description clearly states it performs a realizable-vs-theoretical edge check against live order book depth. Differentiates between single-market and basket modes, and explicitly distinguishes from sibling tools polymarket_arbitrage and polymarket_edges by stating 'USE THIS before acting on any polymarket_arbitrage...'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly advises when to use: before acting on polymarket_arbitrage signals or polymarket_edges trades above ~$500. Explains the rationale: theoretical overround may not be capturable and partial fills create directional risk.

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

All Always Seven 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

A3.8/5.0
Disambiguation2/5

Several tools overlap heavily: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all route natural-language questions to the same underlying 5,708-tool catalog, and ask_pipeworx_beta is explicitly identical today. The Polymarket family (bet_research, polymarket_edges, polymarket_arbitrage, polymarket_fill_risk, polymarket_edge_tracker, polymarket_kalshi_spread) also has fuzzy boundaries — both bet_research and polymarket_edges claim 'should I bet on X', and discover_tools versus suggest_questions both serve discovery. Despite very detailed descriptions, an agent would frequently struggle to pick the correct tool.

Naming Consistency3/5

The naming is mostly snake_case and readable, with coherent micro-families (polymarket_*, pipeworx_*, ask_pipeworx variants, remember/recall/forget). However, patterns are mixed: verb_noun (compare_entities, resolve_entity, generate_llms_txt) sits alongside noun-led names (entity_profile, recent_alerts, pipeworx_trending), and entity-related tools use three different conventions (compare_entities, resolve_entity, entity_profile). It's consistent within families but not across the full set.

Tool Count2/5

32 tools is well past the 25-tool threshold for a coherent set, and the scope is a scattered grab bag: a joke RNG, an AI-visibility probe, a 5,708-tool data router, prediction-market arb analytics, key-value memory, subscriptions, npm dependency scanning, llms.txt generation, and a feedback channel. Some of these are arguably platform additions rather than core tools, but as presented the count feels bloated and unfocused.

Completeness3/5

The major workflow areas are well covered — data lookup has routing, grounded mode, deep research, entity resolution, comparisons, profiles, and change feeds; memory and subscriptions each have full lifecycle coverage. However, the server repeatedly references pipeworx:// citation URIs as fetchable yet provides no record-fetching tool, and the diffuse purpose makes it hard to assess what 'complete' even means. Notable gaps exist around citation resolution and execution of the arbitrage signals the Polymarket tools generate.

Resources