Skip to main content
Glama

Abn Lookup

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. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond that: it explains that basket fills can strand the user unhedged, that returns include per-leg fill detail and thin_legs[], and that size_usd is clamped 10–1,000,000. It would earn a 5 if it stated whether the CLOB check is point-in-time or subscribes to live updates, but the added risk disclosure is substantial.

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?

The description is dense but well-organized: mode requirements are front-loaded, single-market and basket behaviors are separated with clear labels, and the risk warning is placed at the end where it reinforces usage. It is longer than typical descriptions, but every sentence carries operational information. A 5 would require slightly better scannability, such as bullet-like breaks for the two modes, but the structure is strong for the 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 description is complete for a high-complexity tool with no output schema: it defines both modes, explains the meaning of size_usd in each mode, lists return fields, identifies risk conditions (thin legs, partial fills, unhedged positions), and gives explicit usage triggers. The only minor gap is not describing the format of apex output or error cases, but with 100% schema coverage and such a rich natural-language spec, no essential call-time information is missing.

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 description coverage is 100%, so the schema already documents all four parameters well, giving a baseline of 3. The tool description goes further by explaining how size_usd is interpreted differently in single-market vs basket mode (spend/proceeds vs settlement notional), and how side default is auto-derived from partition sum in basket mode. This adds meaning beyond the schema, so a 4 is appropriate, though it falls short of 5 because the description doesn't give examples of slug/URL formats or clarify whether market and event are mutually exclusive beyond 'REQUIRES one of'.

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 identifies the tool as a fill-risk/edge-capture check against live CLOB order-book depth, with explicit modes (single-market vs basket) and a specific verb ('checks', 'walks the ladder'). It distinguishes itself from siblings by naming polymarket_arbitrage and polymarket_edges as tools it should precede, so an agent can differentiate it from those alternatives.

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?

The description explicitly says 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500', giving both a clear trigger condition and a specific alternative context. It also explains when not to rely on theoretical overround, which is strong when-to-use guidance.

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

All Abn Lookup 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 have unclear or overlapping boundaries: ask_pipeworx and ask_pipeworx_beta are explicitly identical right now, while ask_pipeworx, deep_research, and validate_claim all handle factual lookup/research tasks. The five polymarket_* tools plus bet_research also overlap enough that an agent could easily pick the wrong entry point despite verbose descriptions.

Naming Consistency3/5

All names are snake_case and generally descriptive, but conventions are mixed: some are verb-first (ask_pipeworx, resolve_entity, validate_claim), some are noun-first (abn_lookup, entity_profile, polymarket_edges), and prefixes like pipeworx_ and polymarket_ are used inconsistently. It is readable but not a clean, predictable pattern.

Tool Count2/5

34 tools is far too many for a server named 'Abn Lookup' — most of the surface is a broad data-research platform with prediction-market analysis, memory, subscriptions, feedback, and web utilities. The count could fit a large platform, but under this server name and with several near-duplicate entry points, it feels bloated.

Completeness4/5

For a read-only lookup/research server, coverage is strong: ABR lookups, entity resolution, single-query research, grounded verification, deep research, company profiles, comparisons, change feeds, prediction-market analysis, memory, and subscriptions are all represented. Minor gaps exist (e.g., no ACN search-by-name, no order execution), but no core workflow dead-ends.

Resources