Skip to main content
Glama
DanielTomaro13

sportsdata-mcp

pointsbet_sgm_price

Read-onlyIdempotent

Price a PointsBet same game multi using your chosen selections. Submit an event key and outcome pairs to get the correlation-adjusted combined price without multiplying individual odds yourself.

Instructions

PRICE A SAME GAME MULTI you choose — give it selections from one PointsBet event, get the correlation-adjusted combined price. Prices combinations PointsBet has not pre-built (for the ones it has, see pointsbet_preprice_multis).

Returns: {success: true, price: 3.6, message: null, invalidSelections: null} — VERIFIED live 2026-08-27 against AFL Western Bulldogs v Collingwood (event 2860313).

THE PRICE IS NOT THE PRODUCT OF THE LEGS, which is the entire reason to ask. Match Result Bulldogs (1.96) with Over 169.5 (1.90) returns 3.60, not 3.724. Combine that same 1.96 with Bulldogs +1.5 (1.90) and it returns 1.96 FLAT — the line leg is implied by the head-to-head, so it is worth nothing, against a naive 3.724. Never multiply PointsBet legs yourself; the error runs to tens of percent.

REDUNDANT LEGS ARE SILENTLY COLLAPSED AND NOTHING SAYS SO. The response has no leg echo at all: a three-leg request priced as two comes back looking identical to a genuine three-leg quote. Unlike TAB, which marks dropped legs redundant, PointsBet gives you no way to detect it from the response. So STATE THE LEGS YOU SENT whenever you report a price, and treat a price that equals the shorter combination's price as evidence a leg was absorbed. Exact duplicates are deduplicated the same silent way.

enableCorrelatedMulti ON THE MARKET IS NOT ELIGIBILITY. It was true on all 82 markets of the verified event, yet the pricer still refused with Market ... event class First Goalscorer - Home is not allowed for Same Game Multi. Only the pricer knows; do not pre-filter on that flag and do not promise a combination before pricing it.

REFUSALS ARRIVE AS HTTP 200 with success: false and price: 0 — the engine raises these rather than passing a zero off as a quote. Three kinds seen live: a suspended or unknown market names the legs in invalidSelections, mutually exclusive legs give OddsFactory returned price 1 or less, and a disallowed market names its event class. An unknown eventKey is the one that does NOT follow the pattern: it 500s.

Example: Price Bulldogs to win with over 169.5 total points {"eventKey": "2860313", "selectedOutcomes": [{"MarketKey": "114096420", "OutcomeKey": "1"}, {"MarketKey": "114104206", "OutcomeKey": "11"}]}

Auth: none needed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
eventKeyYesNumeric event key as a STRING, e.g. "2860313" — the `key` from pointsbet_event or any events feed. Every selection must belong to this event.
selectedOutcomesYesThe legs: [{"MarketKey": "114096420", "OutcomeKey": "1"}, …]. Both come from pointsbet_event — MarketKey is `fixedOddsMarkets[].key`, OutcomeKey is that market's own `outcomes[].key`. OutcomeKey IS ONLY UNIQUE WITHIN ITS MARKET (key "11" is a different bet in each of two markets on the verified event), so the PAIR identifies a leg and an OutcomeKey carried to the wrong MarketKey silently prices something else. Send them as strings. One leg is accepted and just returns that leg's own price.
Install Server

TDQS

A4.6/5.0
Behavior5/5

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

Even though annotations already declare readOnlyHint, openWorldHint, and idempotentHint, the description adds substantial behavioral detail beyond those flags. It explains redundant legs are silently collapsed with no echo, refusals arrive as HTTP 200 with success:false, and the interaction with eventKey 500s. This is exactly the kind of context annotations cannot convey, and it does not contradict the 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?

The description is verbose, but every paragraph earns its place by covering a distinct critical aspect: the correlation-adjusted price, silent leg collapse, eligibility flag caveat, refusal patterns, and an example. It is front-loaded with the core purpose and key warning, then structured into label-headed paragraphs. Slightly long for a tool description, but well-organized and information-dense.

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?

For a tool of this complexity (custom SGM pricing with non-obvious failure modes), the description is fully complete. It includes a verified example with actual keys, explains the return shape, documents all observed refusal types, and covers the only case that does not follow the pattern (unknown eventKey 500s). No output schema exists, but the description provides enough to use the tool correctly.

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?

Schema coverage is 100%, and the input schema already thoroughly documents both parameters, including the critical warning that OutcomeKey is only unique within its market and that the pair is required. The description adds no new parameter semantics beyond what the schema provides; it even repeats the same warning verbatim. Baseline 3 is appropriate since the schema does the heavy lifting.

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 clear, specific verb-resource pair: 'PRICE A SAME GAME MULTI you choose — give it selections from one PointsBet event, get the correlation-adjusted combined price.' It distinguishes from the sibling tool pointsbet_preprice_multis by explicitly stating it covers combinations PointsBet has not pre-built. The purpose is unambiguous and differentiated.

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 states exactly when to use this tool: 'Prices combinations PointsBet has not pre-built (for the ones it has, see pointsbet_preprice_multis).' It also warns against multiplying legs yourself ('Never multiply PointsBet legs yourself') and cautions that `enableCorrelatedMulti` is not eligibility. This gives clear, actionable guidance and exclusion criteria.

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

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/DanielTomaro13/sportsdata-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server