canli-validation-mcp

Validate paper evidence

validate_paper_evidence

Validate paper-evidence structure and disclosures. In local mode, verify signatures, source hashes, and recomputed claims from a signed journal; files stay local.

Instructions

Checks paper-evidence.v0 structure and disclosures. With CANLI_LOCAL=1, record_file reads an export bundle and journal_file verifies signatures, source hashes and recomputed claims. Without a journal, source facts and signatures are unchecked. Local files are never uploaded. This verdict is about the series exactly as submitted. The service never saw the data source, its costs, survivorship, or any lookahead in how the series was built.

Input Schema

TableJSON Schema

Name	Required	Description
`record`	No	A canli.paper-evidence.v0 record.
`signature`	No	Detached record signature for a signed inline record; requires journal_file.
`record_file`	No	Local record or export-bundle JSON path; requires CANLI_LOCAL=1.
`journal_file`	No	Local signed journal to recompute and bind; requires CANLI_LOCAL=1.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	No
`note`	No
`error`	No
`limits`	No
`receipt`	No
`computed`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedv0.13.0Oct 7, 2026

removedInput schema / properties / record / additionalProperties
```
Removed value: -{}
```
removedInput schema / properties / record / propertyNames
```
Removed value: -{
-  "type": "string"
-}
```
removedOutput schema / additionalProperties
```
Removed value: -{}
```
removedOutput schema / properties / data / additionalProperties
```
Removed value: -{}
```

changedOutput schema / properties / error / anyOf

Previous value: -[
-  {
-    "additionalProperties": {},
-    "properties": {},
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "properties": {},
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

changedOutput schema / properties / receipt / anyOf

Previous value: -[
-  {
-    "additionalProperties": {},
-    "properties": {},
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "properties": {},
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

Changed4 schema fields changedv0.12.0Oct 5, 2026

addedInput schema / properties / journal_file

Added value: +{
+  "description": "Local signed journal to recompute and bind; requires CANLI_LOCAL=1.",
+  "maxLength": 1000,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / record_file

Added value: +{
+  "description": "Local record or export-bundle JSON path; requires CANLI_LOCAL=1.",
+  "maxLength": 1000,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / signature

Added value: +{
+  "additionalProperties": false,
+  "description": "Detached record signature for a signed inline record; requires journal_file.",
+  "properties": {
+    "public_key": {
+      "maxLength": 64,
+      "type": "string"
+    },
+    "scheme": {
+      "const": "Ed25519",
+      "type": "string"
+    },
+    "signature": {
+      "maxLength": 128,
+      "type": "string"
+    }
+  },
+  "required": [
+    "scheme",
+    "public_key",
+    "signature"
+  ],
+  "type": "object"
+}

removedInput schema / required
```
Removed value: -[
-  "record"
-]
```

Changed2 schema fields changedv0.10.1Sep 30, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "description": "data.result holds the statistics (data.plain_reading states them); limits say what the result does not establish; receipt ({id, url}) is the signed record, null when none was stored; error ({code, message}) is set only on refusal.",
+  "properties": {
+    "computed": {
+      "type": "string"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {},
+      "type": "object"
+    },
+    "error": {
+      "anyOf": [
+        {
+          "additionalProperties": {},
+          "properties": {},
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "limits": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "note": {
+      "type": "string"
+    },
+    "receipt": {
+      "anyOf": [
+        {
+          "additionalProperties": {},
+          "properties": {},
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}

Changed1 schema field changedv0.6.0Sep 26, 2026
- addedInput schema / properties / record / description
```
Added value: +"A canli.paper-evidence.v0 record."
```
First observedv0.5.0Sep 25, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations give a baseline (non-read-only, non-destructive, open-world), and the description adds real context beyond them: local files are never uploaded, CANLI_LOCAL=1 gates record_file/journal_file behavior, and unsigned/unjournalled inputs leave facts and signatures unchecked. It also pre-empts a misread of the verdict ('about the series exactly as submitted'). This is meaningful behavioral disclosure.

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?

Four tight sentences, front-loaded with the purpose, then mode behavior, then the scope limitation of the verdict. Every sentence carries information, though the closing sentence about survivorship and lookahead is dense enough to need a second read.

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 the important gaps for a validation tool: local-file handling, the journal requirement, and the boundary of what the verdict does and does not prove. Complete for its complexity.

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 the schema already documents the CANLI_LOCAL and journal_file requirements for each parameter, so the description largely restates that gating. Baseline 3 is appropriate; the prose adds only framing, not new syntax or format detail.

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?

States a specific verb+resource ('Checks paper-evidence.v0 structure and disclosures') and names the exact format version it operates on, which naturally separates it from the validate_backtest_length / validate_deflated_sharpe family of numeric validators. It stops short of naming a sibling it is not, so it is clear but not maximally differentiated.

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?

The description implies usage via the CANLI_LOCAL=1 mode and the journal/no-journal branch, and notes the consequence of omitting a journal (source facts and signatures unchecked). However it never states the plain when-to-use condition or points to an alternative tool such as verify_receipt, so guidance is implied rather than explicit.

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