Synthex Forge — x402 Paid Agent Services

Evaluate Statistical Significance

evaluate_statistical_significance

Read-onlyIdempotent

Return ONE signed, dated significance test. use it rather than evaluate_portfolio_verdict for statistical significance, not portfolio verdict; an object with 40 fields including adjusted_p, alpha. $0.05 USDC.

Input Schema

Name	Required	Description	Default
`null`	No	The null this operation operates on. See the schema for its type and whether it is required.	zero_mean
`seed`	No	The random seed, so a stochastic answer can be reproduced exactly.
`as_of`	No	The date the answer is computed as of (YYYY-MM-DD). Defaults to today. Use it to reproduce a past answer exactly.
`trials`	No	The trials this operation operates on. See the schema for its type and whether it is required.
`returns`	No	What the caller wants back.
`benchmark_returns`	No	The return series to benchmark against.

Output Schema

Name	Required	Description
`why`	No	The `why` field of the response.
`name`	No	The `name` field of the response.
`note`	No	A note on how the answer was produced.
`null`	No	The `null` field of the response.
`seed`	No	The `seed` field of the response.
`test`	No	The `test` field of the response.
`alpha`	No	The `alpha` field of the response.
`as_of`	No	The date the answer is computed as of.
`route`	No	The `route` field of the response.
`detail`	Yes	Human-readable explanation of the verdict.
`key_id`	No	The `key_id` field of the response.
`method`	No	The `method` field of the response.
`seeded`	No	The `seeded` field of the response.
`t_stat`	No	The `t_stat` field of the response.
`p_value`	No	The `p_value` field of the response.
`reasons`	No	The `reasons` field of the response.
`verdict`	Yes	The decision this tool returned.
`readOnly`	No	The `readOnly` field of the response.
`verdicts`	No	The `verdicts` field of the response.
`signature`	Yes	The Ed25519 signature over the evidence core, base64-encoded.
`signed_by`	No	The key id that signed the answer.
`statistic`	No	The `statistic` field of the response.
`adjusted_p`	No	The `adjusted_p` field of the response.
`correction`	No	The `correction` field of the response.
`public_key`	No	The `public_key` field of the response.
`significant`	No	The `significant` field of the response.
`observations`	No	The `observations` field of the response.
`coverage_gaps`	No	The `coverage_gaps` field of the response.
`evidence_core`	Yes	The canonical, signed core of the answer — the payload the signature covers.
`output_sha256`	Yes	SHA-256 hex digest of the canonical evidence core.
`test_sidedness`	No	The `test_sidedness` field of the response.
`canonicalization`	No	The canonicalisation rule the digest was computed under.
`classical_t_stat`	No	The `classical_t_stat` field of the response.
`minimum_required`	No	The `minimum_required` field of the response.
`classical_p_value`	No	The `classical_p_value` field of the response.
`correction_factor`	No	The `correction_factor` field of the response.
`permutationTrials`	No	The `permutationTrials` field of the response.
`permutation_trials`	No	The `permutation_trials` field of the response.
`minimumObservations`	No	The `minimumObservations` field of the response.
`signature_algorithm`	No	The `signature_algorithm` field of the response.

Schema Changelog

Changes observed during successful MCP inspections.

Changed42 schema fields changedOct 31, 2026

addedOutput schema / properties / adjusted_p

Added value: +{
+  "description": "The `adjusted_p` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / alpha

Added value: +{
+  "description": "The `alpha` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / as_of

Added value: +{
+  "description": "The date the answer is computed as of.",
+  "type": "string"
+}

addedOutput schema / properties / canonicalization

Added value: +{
+  "description": "The canonicalisation rule the digest was computed under.",
+  "type": "string"
+}

addedOutput schema / properties / classical_p_value

Added value: +{
+  "description": "The `classical_p_value` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / classical_t_stat

Added value: +{
+  "description": "The `classical_t_stat` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / correction

Added value: +{
+  "description": "The `correction` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / correction_factor

Added value: +{
+  "description": "The `correction_factor` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / coverage_gaps

Added value: +{
+  "description": "The `coverage_gaps` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / detail

Added value: +{
+  "description": "Human-readable explanation of the verdict.",
+  "type": "string"
+}

addedOutput schema / properties / evidence_core

Added value: +{
+  "description": "The canonical, signed core of the answer — the payload the signature covers.",
+  "type": "object"
+}

addedOutput schema / properties / key_id

Added value: +{
+  "description": "The `key_id` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / method

Added value: +{
+  "description": "The `method` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / minimumObservations

Added value: +{
+  "description": "The `minimumObservations` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / minimum_required

Added value: +{
+  "description": "The `minimum_required` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / name

Added value: +{
+  "description": "The `name` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / note

Added value: +{
+  "description": "A note on how the answer was produced.",
+  "type": "string"
+}

addedOutput schema / properties / null

Added value: +{
+  "description": "The `null` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / observations

Added value: +{
+  "description": "The `observations` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / output_sha256

Added value: +{
+  "description": "SHA-256 hex digest of the canonical evidence core.",
+  "type": "string"
+}

addedOutput schema / properties / p_value

Added value: +{
+  "description": "The `p_value` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / permutationTrials

Added value: +{
+  "description": "The `permutationTrials` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / permutation_trials

Added value: +{
+  "description": "The `permutation_trials` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / public_key

Added value: +{
+  "description": "The `public_key` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / readOnly

Added value: +{
+  "description": "The `readOnly` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / reasons

Added value: +{
+  "description": "The `reasons` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / route

Added value: +{
+  "description": "The `route` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / seed

Added value: +{
+  "description": "The `seed` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / seeded

Added value: +{
+  "description": "The `seeded` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / signature

Added value: +{
+  "description": "The Ed25519 signature over the evidence core, base64-encoded.",
+  "type": "string"
+}

addedOutput schema / properties / signature_algorithm

Added value: +{
+  "description": "The `signature_algorithm` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / signed_by

Added value: +{
+  "description": "The key id that signed the answer.",
+  "type": "string"
+}

addedOutput schema / properties / significant

Added value: +{
+  "description": "The `significant` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / statistic

Added value: +{
+  "description": "The `statistic` field of the response.",
+  "type": "object"
+}

removedOutput schema / properties / status

Removed value: -{
-  "type": "string"
-}

addedOutput schema / properties / t_stat

Added value: +{
+  "description": "The `t_stat` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / test

Added value: +{
+  "description": "The `test` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / test_sidedness

Added value: +{
+  "description": "The `test_sidedness` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / verdict

Added value: +{
+  "description": "The decision this tool returned.",
+  "type": "string"
+}

addedOutput schema / properties / verdicts

Added value: +{
+  "description": "The `verdicts` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / why

Added value: +{
+  "description": "The `why` field of the response.",
+  "type": "object"
+}

addedOutput schema / required

Added value: +[
+  "detail",
+  "evidence_core",
+  "output_sha256",
+  "signature",
+  "verdict"
+]

AddedOct 31, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuinely useful context beyond that: results are signed and dated, reproducibility is implied, the response carries 40 fields including adjusted_p and alpha, and there is an explicit $0.05 USDC cost — the kind of pricing/auth detail annotations never carry.

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

Conciseness3/5

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

It is short, but the structure is sloppy: the second sentence begins lowercase and crams routing advice and return-shape into one run-on. Front-loading is fine, yet the sentence boundary damage costs readability for an otherwise two-sentence description.

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

Completeness3/5

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

An output schema exists, so the description needn't enumerate return fields — yet it mentions '40 fields including adjusted_p, alpha' anyway while omitting what the actual test or null hypothesis is. For a six-parameter statistics tool, the agent still lacks a statement of which test is computed and how null/trials interact.

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 six parameters are documented in the schema, and the description adds no parameter-level detail (nothing on null, trials, seed, or benchmark_returns). Baseline 3 applies when the schema does all the work.

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 first sentence states a specific verb and resource ('Return ONE signed, dated significance test') and the second names the sibling it is not (evaluate_portfolio_verdict). The agent can distinguish it from the verdict-family tools, though the phrase 'ONE signed, dated significance test' is slightly cryptic about what test is actually run.

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 explicitly routes the agent: 'use it rather than `evaluate_portfolio_verdict` for statistical significance, not portfolio verdict' gives both the preferred tool and the exclusion condition. No other siblings are addressed, and the garbled punctuation makes the routing sentence harder to parse than it should be.

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

All Synthex Forge — x402 Paid Agent Services 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.