Prediction Markets Quant

The Ladder — NFL strike ladders: every Kalshi strike vs the PMP distribution

nfl_ladder

Read-only

Use for "where does the model disagree with Kalshi on the Rams spread" and "biggest ladder gaps this week". Every NFL strike ladder — spreads, season win totals, player props — with Kalshi's price at each strike beside our distribution and a SHAPE / LOCATION / PRICED / PARTIAL verdict. Our number is published only between 30% and 70%.

Input Schema

TableJSON Schema

Name	Required	Description
`kind`	No	Verdict filter. One of: shape · location · agree · partial.
`team`	No	Team abbrev (SEA, LAR, JAX) — ladders involving that club.
`limit`	No	Max ladders (default 8). Values above 25 are clamped to 25.
`family`	No	Ladder family. Omit for all three. One of: spread · season_wins · props.
`player`	No	Player name (partial, case-insensitive) — prop ladders only.

Output Schema

TableJSON Schema

Name	Required	Description
`rows`	No	Ladders: subject, stat, verdict, and each rung with market and model (model only inside the published band).
`week`	No	NFL week.
`count`	No	Ladders returned.
`sources`	No
`tell_user`	No	Show this sentence to the user first.
`timestamp`	No
`needs_input`	No
`example_call`	No
`data_freshness`	No
`published_band`	No	{ lo, hi } — our probability is published only inside this band.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 15, 2026

removedInput schema / properties / limit / anyOf

Removed value: -[
-  {
-    "anyOf": [
-      {
-        "type": "number"
-      },
-      {
-        "type": "string"
-      }
-    ]
-  },
-  {
-    "type": "null"
-  }
-]

addedInput schema / properties / limit / type

Added value: +[
+  "number",
+  "string",
+  "null"
+]

Changed8 schema fields changedOct 6, 2026

addedInput schema / properties / family / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "enum": [
+      "spread",
+      "season_wins",
+      "props"
+    ],
+    "type": "string"
+  }
+]

changedInput schema / properties / family / description

Previous value: -"Ladder family. Omit for all three."New value: +"Ladder family. Omit for all three. One of: spread · season_wins · props."

removedInput schema / properties / family / enum

Removed value: -[
-  "spread",
-  "season_wins",
-  "props"
-]

removedInput schema / properties / family / type
```
Removed value: -"string"
```

addedInput schema / properties / kind / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "enum": [
+      "shape",
+      "location",
+      "agree",
+      "partial"
+    ],
+    "type": "string"
+  }
+]

changedInput schema / properties / kind / description

Previous value: -"Verdict filter."New value: +"Verdict filter. One of: shape · location · agree · partial."

removedInput schema / properties / kind / enum

Removed value: -[
-  "shape",
-  "location",
-  "agree",
-  "partial"
-]

removedInput schema / properties / kind / type
```
Removed value: -"string"
```

Changed6 schema fields changedOct 1, 2026

addedInput schema / properties / limit / anyOf

Added value: +[
+  {
+    "anyOf": [
+      {
+        "type": "number"
+      },
+      {
+        "type": "string"
+      }
+    ]
+  },
+  {
+    "type": "null"
+  }
+]

removedInput schema / properties / limit / default
```
Removed value: -8
```

changedInput schema / properties / limit / description

Previous value: -"Max ladders (default 8)."New value: +"Max ladders (default 8). Values above 25 are clamped to 25."

removedInput schema / properties / limit / maximum
```
Removed value: -25
```
removedInput schema / properties / limit / minimum
```
Removed value: -1
```
removedInput schema / properties / limit / type
```
Removed value: -"integer"
```

Changed1 schema field changedSep 29, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "properties": {
+    "count": {
+      "description": "Ladders returned."
+    },
+    "data_freshness": {},
+    "example_call": {},
+    "needs_input": {},
+    "published_band": {
+      "description": "{ lo, hi } — our probability is published only inside this band."
+    },
+    "rows": {
+      "description": "Ladders: subject, stat, verdict, and each rung with market and model (model only inside the published band)."
+    },
+    "sources": {},
+    "tell_user": {
+      "description": "Show this sentence to the user first.",
+      "type": "string"
+    },
+    "timestamp": {
+      "type": "string"
+    },
+    "week": {
+      "description": "NFL week."
+    }
+  },
+  "type": "object"
+}

AddedSep 8, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, so the safety profile is covered. The description adds genuine behavioral context beyond that: the model's number is only published between 30% and 70%, and outputs carry a SHAPE/LOCATION/PRICED/PARTIAL verdict — both are things an agent needs to interpret results.

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

Conciseness4/5

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

Front-loaded with the 'Use for' cue and two sentences that each carry content — resource, contents, verdict taxonomy, and the publication constraint. The example queries are slightly verbose but earn their place by grounding the use case.

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?

An output schema exists, so return values need no explanation, and the description covers purpose, families, verdicts, and the 30-70% constraint. The remaining gap is the verdict term mismatch with the schema enum and lack of any note on default/clamp behavior referenced in the schema.

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%, so the schema already documents all five filters, and the baseline is 3. The description adds little, and worse it introduces a conflicting label: it lists the verdict as 'PRICED' while the `kind` enum uses 'agree', which could mislead an agent filtering on that value.

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?

States a specific resource (NFL strike ladders — spreads, season win totals, player props) and specific content (Kalshi's price at each strike beside our distribution plus a verdict). The example queries ('where does the model disagree with Kalshi on the Rams spread') make the tool's function unambiguous and separable from generic edge tools like nfl_edge or ladder_arb.

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?

The 'Use for ...' framing supplies two concrete triggering questions, giving clear context for when to reach for this tool. However, it names no alternatives or exclusions, leaving the agent to infer when explain_ladder or ladder_arb would be the better choice.

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

All Prediction Markets Quant tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.