Skip to main content
Glama

Resolution Diff

resolution_diff
Read-onlyIdempotent

Field-by-field diff of TWO markets' settlement clauses (one from each of a and b; either can be Polymarket .com, Polymarket US, or Kalshi), runs resolution_audit on both sides and compares source, settle time, precision, comparison_basis, and evidence standard. Returns equivalent: "true" only when both sides parsed with enough confidence to compare AND no field conflicts; "false" when a specific conflict was found (differing_fields names which, e.g. ["source","settle_time"] for a Polymarket Bitcoin market settling on Binance's 1-minute candle at noon ET versus a Kalshi KXBTCD market settling on CF Benchmarks' BRTI 60-second average at 5pm EDT, SAME asset, DIFFERENT contract; or ["source","precision"] for Polymarket.com's Chainlink 15-minute TWAP clause (precision "twap_60s_lookback") against Kalshi's 15-minute KXBTC15M clause (precision "60-second trailing average" off CF Benchmarks' BRTI), different source and a different lookback mechanism, even though BOTH compare an end-of-window average to a start-of-window average, so comparison_basis is EQUAL there and correctly NOT in differing_fields, verified live 2026-10-22, fleet #3447); "unclear" when one or both sides could not be confidently parsed (an absence of evidence is not evidence of equivalence, read raw_clause yourself in that case). comparison_basis is flagged as differing whenever both sides resolved one and they disagree, independent of whether source/precision also matched. Only flags source/evidence_standard as differing when BOTH sides gave a SPECIFIC comparable answer, a named source (e.g. "Associated Press, Fox News, NBC") against a generic one (e.g. Kalshi's "consensus of media organizations") is treated as the same evidence standard, not a conflict, since that is standard election-market boilerplate on both venues. Use this before sizing a polymarket_kalshi_spread pair as a real cross-venue arb, or standalone to sanity-check any two markets you suspect settle on different things.

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": {
      "a": {
        "venue": "polymarket",
        "market": "bitcoin-above-70k-on-september-13-2026"
      },
      "b": {
        "venue": "kalshi",
        "market": "KXBTCD-26SEP1317"
      }
    },
    "name": "resolution_diff"
  }
}

Input Schema

NameRequiredDescriptionDefault
aYesFirst market to compare.
bYesSecond market to compare.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / a / properties / venue / enum
      Previous value: -[
      -  "polymarket",
      -  "kalshi"
      -]New value: +[
      +  "polymarket",
      +  "kalshi",
      +  "polymarket-us"
      +]
    • changedInput schema / properties / b / properties / venue / enum
      Previous value: -[
      -  "polymarket",
      -  "kalshi"
      -]New value: +[
      +  "polymarket",
      +  "kalshi",
      +  "polymarket-us"
      +]
  2. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already cover read-only, idempotent, and open-world traits, and the description adds substantial meaning beyond them: the three-valued `equivalent` outcome and what causes each, the fact that differing_fields names conflicting fields, and the non-obvious rule that a named-source clause versus a generic 'consensus of media' clause is not a conflict. The caution that 'an absence of evidence is not evidence of equivalence' and the instruction to read raw_clause directly is exactly the kind of behavioral caveat an agent would otherwise get wrong.

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

Conciseness2/5

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

The purpose is front-loaded, but the body is one enormous run-on sentence riddled with nested parentheticals, live-verification metadata ('verified live 2026-10-22, fleet #3447'), and fully worked examples inline. The detail about differing_fields semantics is valuable, yet it should have been broken into short, scannable sentences rather than buried inside a 250-word clause.

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

Completeness4/5

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

There is no output schema, so the description must explain return values — and it does, defining `equivalent` true/false/unclear, differing_fields, and raw_clause. Combined with the mutation-free annotations, an agent has what it needs to call and interpret the tool, though the flagging rules are harder to apply than necessary due to structure.

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%, with nested a/b objects, venue enums, and a worked example, so the structured data already carries most of the load. The description adds only that the two inputs are one market each and that either side may be Polymarket .com, Polymarket US, or Kalshi — useful but marginal over the schema's enum.

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 specific verb and resource: 'Field-by-field diff of TWO markets' settlement clauses', and immediately clarifies the composition of the two inputs and the mechanism (it 'runs resolution_audit on both sides and compares source, settle time, precision, comparison_basis, and evidence standard'). This clearly distinguishes it from the single-market sibling resolution_audit and from polymarket_kalshi_spread.

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

Usage Guidelines4/5

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

It gives a concrete trigger ('Use this before sizing a polymarket_kalshi_spread pair as a real cross-venue arb') plus a standalone use case ('sanity-check any two markets you suspect settle on different things'), which routes the agent well. It stops short of stating when not to use it or explicitly contrasting with resolution_audit for single-market checks, so it falls just under a full 5.

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.