Skip to main content
Glama

NS Pros MCP Gateway

nsf-awards__updown_divergence_rate

How often two venues settled the SAME 15-minute crypto window differently, over every settled window on record. Compares polymarket.com (Chainlink TWAP) with Kalshi and with Polymarket US (both CF Benchmarks BRTI), and Kalshi with Polymarket US as the same-feed control. Per pair: windows both venues settled, divergent count, the rate with its 95% Wilson interval (withheld under 30 paired windows), which direction they split, and what was excluded (unsettled on a side, 50-50). A HEADLINE RATE IS

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "days": 30,
      "asset": "btc"
    },
    "name": "nsf-awards__updown_divergence_rate"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoLook-back in days, 1-90 (default 30). The archive starts 2026-09-22 (polymarket.com, Kalshi) and 2026-10-07 (Polymarket US, btc), so a longer span is capped by what is held; coverage is reported per pair.
assetNobtc (default) | eth | sol | xrp | bnb. The archive holds btc/eth on all three venues, sol/xrp on polymarket.com and Polymarket US, bnb on Kalshi only (no pair).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does substantively well: it discloses the statistical method (95% Wilson interval), an explicit suppression rule (withheld under 30 paired windows), the reporting of direction of split, and the exact exclusion categories (unsettled on a side, 50-50). That is real behavioral context beyond the signature. The missing piece is the cut-off final clause about the headline rate, which likely carried a caveat the agent now cannot see.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

The core is a single dense but well-ordered sentence, and the venue/feed mapping is front-loaded where it matters. However, the definition ends mid-sentence at "A HEADLINE RATE IS ", which is a structural defect that leaves a dangling claim, and the pair enumeration is packed tightly enough to require re-reading.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-optional-parameter analytical tool with no output schema, the description does describe the return shape well: per-pair counts, rate, interval, direction, and exclusions, plus coverage reporting. But the truncation removes whatever qualification the headline rate carried, and with no annotations and no output schema there is no fallback source for that missing behavior. Complete enough to call correctly, not complete enough to interpret confidently.

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 both parameter descriptions are already detailed, including the archive start dates and per-venue asset coverage. The description adds essentially nothing parameter-level beyond restating that polymarket.com uses Chainlink TWAP and the other two use CF Benchmarks BRTI, which is venue semantics rather than parameter semantics. Baseline 3 is correct.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"How often two venues settled the SAME 15-minute crypto window differently" is a specific, concrete statement of the computed statistic, and the following sentence enumerates the exact venue pairs being compared. The agent knows precisely what the tool measures. It stops short of 5 because the truncated final sentence ("A HEADLINE RATE IS ") leaves the headline summary's identity unresolved.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: the description makes clear this is a cross-venue settlement-consistency analysis, which tells the agent what question it answers. But there is no explicit when-to-use/when-not, no statement of what a non-diverging or unpairable asset means for calling it, and no routing to alternatives. Sibling names here are per-provider clones, so no meaningful differentiation is offered or required.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.