Canli Validation

Data-snooping tests (SPA, Reality Check, StepM)

validate_reality_check

Data-snooping tests on every variant a search tried: Hansen's SPA p-value that the best beat the benchmark only by luck, White's Reality Check, and the variants Romano-Wolf StepM finds better. Send all variants tried, not only the winners. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.

Input Schema

TableJSON Schema

Name	Required	Description
`reps`	No	Bootstrap draws; default 2000.
`seed`	No	Sampling seed; default 42.
`alpha`	No	Familywise error for StepM; default 0.05.
`matrix`	No	Returns of every variant the search tried, one row per period, one column per variant.
`benchmark`	No	Benchmark return per period; default zero.
`matrix_file`	No	Path to a CSV or JSON with one numeric column per variant, instead of matrix.
`block_length`	No	Mean bootstrap block in periods; default round(n^(1/3)).

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 changedOct 4, 2026

removedInput schema / properties / seed / maximum
```
Removed value: -9007199254740991
```
removedInput schema / properties / seed / minimum
```
Removed value: --9007199254740991
```
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"
+  }
+]

AddedSep 28, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, so the safety profile is partly covered externally. The description adds interpretive context — that a deflated Sharpe or overfitting probability crossing a threshold is neither an admission nor a forecast — which is genuine value beyond the annotations. It discloses no cost, runtime, or bootstrap-behavior details, so with annotations present a 3 is appropriate.

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?

Three sentences, purpose front-loaded with the three test names, then the input requirement, then the interpretive caveat. No filler, though the final sentence is semantically loose (mixing deflated Sharpe, overfitting, and 'not a forecast' into one clause) and is more cautionary than actionable.

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

Completeness5/5

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 explained. The description covers what distinguishes this test family, the critical input requirement, and the interpretive limits of the result — enough for a zero-required-parameter, fully schema-documented tool. Nothing an agent needs to invoke it correctly is missing.

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%, so all seven parameters (reps, seed, alpha, matrix, benchmark, matrix_file, block_length) are already documented with defaults and ranges in the schema. The description only reinforces one of them via 'all variants tried' and implies matrix_file can substitute for matrix. Baseline 3 for a fully documented schema.

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?

The description names specific tests (Hansen's SPA, White's Reality Check, Romano-Wolf StepM) operating on a clearly stated resource — the returns of every variant a search tried. That is a concrete verb+resource combination an agent can recognize. It does not, however, explicitly route the agent away from the many validate_* siblings (deflated Sharpe, luck_trials, overfitting); it only references a deflated Sharpe as a caveat rather than as an alternative.

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?

There is one strong usage requirement — 'Send all variants tried, not only the winners' — which tells the agent the precondition for a valid run, and the scope statement ('on every variant a search tried') implies the data-snooping scenario. But no alternatives are compared or excluded, and the borderline case of many trials vs. the sibling overfitting/deflated-Sharpe tools is left implicit.

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

All Canli Validation 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.