Free-text front door — any sports/markets question, routed + answered [PAID — signal credit or x402 USDC. Cost: 1 signal credit ($1.70-$2.49/credit by pack size). Uncredentialed calls return the 402 payment envelope; set X-API-KEY on the MCP connection or pay x402 out-of-band at GET /api/scan/ask.]
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It clearly discloses the paid nature, exact cost, authentication expectations, and the 402 payment-envelope behavior for uncredentialed calls. However, it does not describe the successful response shape or potential side effects beyond 'answered.'
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 front-loads the core purpose in the first clause and then packs payment, auth, and error behavior into a compact bracket. It is dense but not wasteful; every sentence serves a purpose, though the payment details add noticeable length.
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?
For a simple free-text tool with no output schema and no annotations, this description covers the essential context: purpose, usage, pricing, authentication, failure mode, and a pointer to parameter docs. It lacks an explicit description of the return value/answer format, but the 'answered' wording implies an unstructured response.
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?
With zero formal parameters, the baseline is 4. The description adds semantic context by calling it 'free-text,' implying a natural-language query input, and the schema description directs users to the 'instruments' tool for per-endpoint parameter docs. No parameter names are given, but with no structured params this is reasonable.
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 opens with 'Free-text front door — any sports/markets question, routed + answered,' which clearly identifies this as a natural-language catch-all ask tool. It distinguishes itself from the structured scan_* and signal_* sibling tools by positioning it as the general entry point for arbitrary questions.
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 phrase 'Free-text front door' gives clear context that this is the right tool for open-ended questions rather than structured, domain-specific scans. It also points users to the 'instruments' tool for parameter documentation, but it does not explicitly name alternatives or say when not to use this tool.
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.
There is significant overlap between scan_* and signal_* tools for the same underlying asset classes, e.g. scan_futures vs signal_futures, scan_racing vs signal_racing, and scan_predmarket vs signal_polymarket. Broader catch-alls like analysis, scan_ask, backtest, and signal_generate also blur the boundary, forcing an agent to parse long pricing details before knowing which tool actually applies.
The overwhelming majority of tools follow a clear `scan_` or `signal_` snake_case prefix, which makes the product families easy to recognize. A small set of standalone unprefixed tools — analysis, backtest, instruments, leaderboard, quote, track_record — breaks the pattern, but the overall scheme is still consistent enough to infer.
47 tools is far beyond the practical range for an agent to reason about, even though the server's domain is broad and heavily segmented. Many specialist endpoints could be consolidated under fewer catch-all scanners and signals, but the exposed surface instead forces a large tool-selection decision on every request.
The tool surface covers discovery, cost preview, sample analysis, public track records, leaderboards, broad market scanning, asset-class-specific scanning, sports and event signals, and prediction-market verticals. There are minor gaps in explicit account/credit management and some redundant paths, but for a signal/research service the workflow is largely complete.