Nonobench

Get puzzle results

get_puzzle_results

Read-only

Per-model outcomes for one puzzle. Answers are omitted unless requested.

Input Schema

TableJSON Schema

Name	Required	Description
`id`	Yes	Puzzle id from list_puzzles
`effort`	No	best, all (default), or one effort level
`family`	No	Comma-separated family ids; empty means no filter
`provider`	No	Comma-separated provider ids; empty means no filter
`reasoning`	No	Only reasoning (true) or non-reasoning (false) variants
`open_weights`	No	Only open-weight (true) or closed (false) models
`include_answers`	No	Include each model's answer grid

Output Schema

TableJSON Schema

Name	Required	Description	Default
`runs`	Yes
`size`	Yes
`index`	Yes
`solved`	Yes
`attempts`	Yes
`puzzleId`	Yes
`updatedAt`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedSep 29, 2026

addedInput schema / properties / effort / description

Added value: +"best, all (default), or one effort level"

addedInput schema / properties / family / description

Added value: +"Comma-separated family ids; empty means no filter"

addedInput schema / properties / id / description
```
Added value: +"Puzzle id from list_puzzles"
```
addedInput schema / properties / include_answers / description
```
Added value: +"Include each model's answer grid"
```

addedInput schema / properties / open_weights / description

Added value: +"Only open-weight (true) or closed (false) models"

addedInput schema / properties / provider / description

Added value: +"Comma-separated provider ids; empty means no filter"

addedInput schema / properties / reasoning / description

Added value: +"Only reasoning (true) or non-reasoning (false) variants"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "attempts": {
+      "type": "number"
+    },
+    "index": {
+      "type": "number"
+    },
+    "puzzleId": {
+      "type": "string"
+    },
+    "runs": {
+      "items": {
+        "additionalProperties": {},
+        "properties": {
+          "answer": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "correct": {
+            "type": "boolean"
+          },
+          "displayName": {
+            "type": "string"
+          },
+          "model": {
+            "type": "string"
+          },
+          "status": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "model",
+          "correct",
+          "status",
+          "displayName"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "size": {
+      "type": "string"
+    },
+    "solved": {
+      "type": "number"
+    },
+    "updatedAt": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "updatedAt",
+    "puzzleId",
+    "index",
+    "size",
+    "attempts",
+    "solved",
+    "runs"
+  ],
+  "type": "object"
+}

First observedSep 29, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description usefully discloses a non-obvious default (answer grids are omitted unless requested), but says nothing about pagination, result volume, or behavior when filters match nothing.

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

Conciseness5/5

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

Two sentences, no waste, with the resource scope front-loaded and the output-default caveat trailing. Every clause earns its place.

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 not be described, and the description covers the resource scope plus the answers-omission behavior. For a 7-param filtered query tool the definition is adequate, though the absence of any usage routing leaves a small gap.

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 description coverage is 100% and there are 7 well-documented parameters, so the schema carries the parameter burden. The description adds nothing about parameter syntax, defaults, or filter interaction beyond what the schema already states.

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?

"Per-model outcomes for one puzzle" gives a specific verb+resource with a clear scope (one puzzle, all models), which implicitly separates it from get_puzzle (single puzzle metadata) and get_model_results (one model across puzzles). It never names a sibling, so differentiation is inferable rather than explicit.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no exclusions, and no routing to alternatives such as get_puzzle or get_model_results. The scoping phrase hints at the context, but the agent must infer when this is the right call.

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

All Nonobench 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.

Resources

Need Help?