list_fair_valuesReturn current no-vig sportsbook-consensus probabilities for supported upcoming markets. Requires a Sorqen key. Free keys receive real values within Free limits; evidence is available on paid plans. Use for scanning/filtering; use get_fair_value for one known outcome.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| cursor | No | ||
| league | No | ||
| market_type | No | ||
| min_confidence | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It usefully reveals the authentication requirement (Sorqen key) and plan-dependent data behavior (free keys get real values within Free limits; evidence on paid plans). It does not mention pagination behavior or rate limits, but it makes the read-only nature and data source clear.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three short sentences with no filler. Purpose is front-loaded, followed by access constraints and sibling differentiation. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers purpose, access requirements, and sibling differentiation, which makes it minimally viable. However, with five optional parameters and no output schema, it lacks details about pagination semantics, the exact return shape, and what 'supported upcoming markets' means. An agent could still call it correctly based on the schema, but with avoidable ambiguity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not explain limit, cursor, league, market_type, or min_confidence. The general 'scanning/filtering' framing hints at the tool's purpose but leaves parameter semantics largely to inference. This is a notable gap for an agent selecting filter values.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Return') and a specific resource ('current no-vig sportsbook-consensus probabilities'), making the tool's purpose immediately clear. It also distinguishes itself from get_fair_value by explicitly framing this tool as for scanning/filtering rather than looking up one known outcome.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit guidance: use this tool for scanning/filtering, and use get_fair_value for a single known outcome. It also adds important usage context about requiring a Sorqen key and free vs. paid plan limits, which helps an agent decide when this tool is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: describe_* covers meta topics, list_* covers discovery, get_* covers retrieval, and grade is a unique action. The descriptions explicitly cross-reference when to use one tool vs another, such as list_fair_values for discovery and get_fair_value for known outcome ids.
Tool names are overwhelmingly consistent snake_case imperative verb_noun pairs (describe_, get_, list_), and grade is a readable verb-only command. The single deviation from verb_noun is minor and does not create confusion.
Ten tools is well-scoped for the server's purpose: meta/explanation tools, discovery tools, retrieval tools, and a grading action. Each tool earns its place without overlapping or feeling like filler.
The tool surface covers the full read-only workflow: discover supported leagues, list and fetch fair values, retrieve history, grade submitted prices, and understand settlement rules, plans, and authentication. There are no obvious dead ends or missing operations for the stated domain.