Skip to main content
Glama

sportiq-mcp

by io.github.Ninjabeam20

cricket_find_value_bets

Read-onlyIdempotent

Compare model probabilities against market-implied IPL odds. Requires THEODDS_KEY.

NOTE: cricket has no calibrated team-strength model wired yet (unlike the football Elo/Poisson path), so this tool currently returns an EMPTY value_bets list — scoring an edge against a neutral 50/50 prior would flag every market underdog, which would be misleading. It still reports how many events were screened so callers know odds were available. For raw de-vigged prices use cricket_get_live_odds. Real edge detection lands when a cricket win model is wired (see cricket_head_to_head).

Args: team: Optional team name to filter events (case-insensitive substring). Omit to scan every IPL odds event. min_edge: Minimum edge (model_prob - devigged_market_prob), 0..1. Default 0.05. Currently informational only (no bets emitted).

Returns: data.value_bets: always [] until a cricket model is wired. data.events_analysed: count of events screened (both teams present). data.model: "neutral_baseline". data.note: why no bets are emitted. meta.estimated: true.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
teamNoOptional team name to filter events (case-insensitive substring). Omit to scan every IPL odds event.
min_edgeNoMinimum edge (model_prob - devigged_market_prob), 0..1. Default 0.05. Currently informational only (no bets emitted).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNo
metaNo
errorNo

Schema Changelog

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

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description discloses the major behavioral caveat: the tool always returns an empty value_bets list because no calibrated cricket model exists. It further explains why a neutral baseline would be misleading, describes the exact return fields (value_bets, events_analysed, model, note, meta.estimated), and reveals the auth requirement. 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.

Conciseness5/5

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

The description is longer than average, but every section earns its place: the caveat is essential to prevent misuse, the alternative routing prevents wasted calls, and the Args/Returns breakdown is compact and scannable. The structure front-loads the most critical behavioral warning before details.

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 with a major behavioral caveat, the description is complete: it covers prerequisites, current stub behavior, why the behavior exists, what callers can rely on, and where to go for alternatives. Even with an output schema present, the explicit description of value_bets always being [] is necessary and provided.

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 description coverage is 100%, so the baseline is 3. The description largely repeats the schema text for team and min_edge, adding no genuinely new semantic detail beyond what is already in the parameter descriptions. It is adequate but does not elevate understanding beyond the schema.

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 states the tool's intent ('Compare model probabilities against market-implied IPL odds') and immediately corrects the expectation by noting the tool currently returns an empty value_bets list. This distinguishes it from siblings like cricket_get_live_odds and football_find_value_bets, and makes its actual role as an odds-screening stub unmistakable.

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 gives explicit guidance: raw prices belong in cricket_get_live_odds, real edge detection will come via cricket_head_to_head once a model is wired, and callers should use the events_analysed count to confirm odds availability. It also notes the THEODDS_KEY prerequisite and explains why the tool should not be relied on for actual bets.

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

All sportiq-mcp 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

A3.6/5.0
Disambiguation3/5

Sport prefixes make the three domains easy to separate, and most tools have clear purposes. However, several tools overlap: football_match_predictor vs football_xg_model, f1_head_to_head_pace vs f1_race_pace_compare, and the cricket fantasy tools (build_dream11, captain_recommendation, differential_picks) all require careful reading to avoid misselection.

Naming Consistency4/5

The sport prefix + snake_case pattern is consistent and retrieval tools uniformly use get_, which creates predictability. The main deviation is that many analysis/model tools are noun phrases rather than verb_noun (cricket_head_to_head, football_knockout_path, f1_tyre_degradation), but they remain readable and scoped.

Tool Count2/5

44 tools is well above the 25+ threshold for a single server and will strain agent context and tool-selection quality. Each sport block is individually reasonable at 13-15 tools, but combining three sports plus cross-sport and health utilities makes the overall surface too large.

Completeness3/5

Core workflows are broadly covered: live data, schedule/standings, match prediction, tournament simulation, fantasy help, and strategy analysis exist for each sport. However, there are notable dead ends: cricket_player_form_index needs a player_id no exposed tool returns, football_get_match_stats requires an API-Football numeric ID not mapped anywhere, and f1_get_lap_times references a stints endpoint that is not exposed as a tool.

Resources