Synthex Forge — x402 Paid Agent Services

Verify Research Independence

verify_research_independence

Read-onlyIdempotent

Verify that a research claim set has more than one source. use it rather than verify_business_screen for research independence, not business screen; an object with 44 fields including action, assessable. $0.05 USDC.

Input Schema

Name	Required	Description	Default
`independence.claims`	No	[POST /v1/data/source-independence]
`independence.similarity_threshold`	No	[POST /v1/data/source-independence]

Output Schema

Name	Required	Description
`id`	No	The `id` field of the folded answer.
`ok`	No	Whether every inner call succeeded.
`ts`	No	The `ts` field of the folded answer.
`size`	No	The `size` field of the folded answer.
`text`	No	The `text` field of the folded answer.
`type`	No	The `type` field of the folded answer.
`index`	No	The `index` field of the folded answer.
`action`	No	The `action` field of the folded answer.
`detail`	No	The `detail` field of the folded answer.
`groups`	No	The `groups` field of the folded answer.
`tokens`	No	The `tokens` field of the folded answer.
`reasons`	No	The `reasons` field of the folded answer.
`results`	No	One result per inner call.
`signals`	No	The `signals` field of the folded answer.
`sources`	No	The `sources` field of the folded answer.
`summary`	No	One-line summary of the folded answer.
`textual`	No	The `textual` field of the folded answer.
`group_id`	No	The `group_id` field of the folded answer.
`problems`	No	The `problems` field of the folded answer.
`source_a`	No	The `source_a` field of the folded answer.
`source_b`	No	The `source_b` field of the folded answer.
`upstream`	No	The `upstream` field of the folded answer.
`exception`	No	The `exception` field of the folded answer.
`reference`	No	The `reference` field of the folded answer.
`timestamp`	No	The `timestamp` field of the folded answer.
`assessable`	No	The `assessable` field of the folded answer.
`claim_count`	No	The `claim_count` field of the folded answer.
`weak_signals`	No	The `weak_signals` field of the folded answer.
`source_a_index`	No	The `source_a_index` field of the folded answer.
`source_b_index`	No	The `source_b_index` field of the folded answer.
`common_upstream`	No	The `common_upstream` field of the folded answer.
`text_similarity`	No	The `text_similarity` field of the folded answer.
`verdict_meaning`	No	The `verdict_meaning` field of the folded answer.
`dependency_edges`	No	The `dependency_edges` field of the folded answer.
`shared_reference`	No	The `shared_reference` field of the folded answer.
`weak_signal_edges`	No	The `weak_signal_edges` field of the folded answer.
`creates_dependency`	No	The `creates_dependency` field of the folded answer.
`dependency_reasons`	No	The `dependency_reasons` field of the folded answer.
`identical_timestamp`	No	The `identical_timestamp` field of the folded answer.
`unassessable_claims`	No	The `unassessable_claims` field of the folded answer.
`reference_is_citable`	No	The `reference_is_citable` field of the folded answer.
`similarity_threshold`	No	The `similarity_threshold` field of the folded answer.
`assessable_claim_count`	No	The `assessable_claim_count` field of the folded answer.
`independent_corroboration_count`	No	The `independent_corroboration_count` field of the folded answer.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 31, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "action": {
+      "description": "The `action` field of the folded answer.",
+      "type": "object"
+    },
+    "assessable": {
+      "description": "The `assessable` field of the folded answer.",
+      "type": "object"
+    },
+    "assessable_claim_count": {
+      "description": "The `assessable_claim_count` field of the folded answer.",
+      "type": "object"
+    },
+    "claim_count": {
+      "description": "The `claim_count` field of the folded answer.",
+      "type": "object"
+    },
+    "common_upstream": {
+      "description": "The `common_upstream` field of the folded answer.",
+      "type": "object"
+    },
+    "creates_dependency": {
+      "description": "The `creates_dependency` field of the folded answer.",
+      "type": "object"
+    },
+    "dependency_edges": {
+      "description": "The `dependency_edges` field of the folded answer.",
+      "type": "object"
+    },
+    "dependency_reasons": {
+      "description": "The `dependency_reasons` field of the folded answer.",
+      "type": "object"
+    },
+    "detail": {
+      "description": "The `detail` field of the folded answer.",
+      "type": "object"
+    },
+    "exception": {
+      "description": "The `exception` field of the folded answer.",
+      "type": "object"
+    },
+    "group_id": {
+      "description": "The `group_id` field of the folded answer.",
+      "type": "object"
+    },
+    "groups": {
+      "description": "The `groups` field of the folded answer.",
+      "type": "object"
+    },
+    "id": {
+      "description": "The `id` field of the folded answer.",
+      "type": "object"
+    },
+    "identical_timestamp": {
+      "description": "The `identical_timestamp` field of the folded answer.",
+      "type": "object"
+    },
+    "independent_corroboration_count": {
+      "description": "The `independent_corroboration_count` field of the folded answer.",
+      "type": "object"
+    },
+    "index": {
+      "description": "The `index` field of the folded answer.",
+      "type": "object"
+    },
+    "ok": {
+      "description": "Whether every inner call succeeded.",
+      "type": "boolean"
+    },
+    "problems": {
+      "description": "The `problems` field of the folded answer.",
+      "type": "object"
+    },
+    "reasons": {
+      "description": "The `reasons` field of the folded answer.",
+      "type": "object"
+    },
+    "reference": {
+      "description": "The `reference` field of the folded answer.",
+      "type": "object"
+    },
+    "reference_is_citable": {
+      "description": "The `reference_is_citable` field of the folded answer.",
+      "type": "object"
+    },
+    "results": {
+      "description": "One result per inner call.",
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "shared_reference": {
+      "description": "The `shared_reference` field of the folded answer.",
+      "type": "object"
+    },
+    "signals": {
+      "description": "The `signals` field of the folded answer.",
+      "type": "object"
+    },
+    "similarity_threshold": {
+      "description": "The `similarity_threshold` field of the folded answer.",
+      "type": "object"
+    },
+    "size": {
+      "description": "The `size` field of the folded answer.",
+      "type": "object"
+    },
+    "source_a": {
+      "description": "The `source_a` field of the folded answer.",
+      "type": "object"
+    },
+    "source_a_index": {
+      "description": "The `source_a_index` field of the folded answer.",
+      "type": "object"
+    },
+    "source_b": {
+      "description": "The `source_b` field of the folded answer.",
+      "type": "object"
+    },
+    "source_b_index": {
+      "description": "The `source_b_index` field of the folded answer.",
+      "type": "object"
+    },
+    "sources": {
+      "description": "The `sources` field of the folded answer.",
+      "type": "object"
+    },
+    "summary": {
+      "description": "One-line summary of the folded answer.",
+      "type": "string"
+    },
+    "text": {
+      "description": "The `text` field of the folded answer.",
+      "type": "object"
+    },
+    "text_similarity": {
+      "description": "The `text_similarity` field of the folded answer.",
+      "type": "object"
+    },
+    "textual": {
+      "description": "The `textual` field of the folded answer.",
+      "type": "object"
+    },
+    "timestamp": {
+      "description": "The `timestamp` field of the folded answer.",
+      "type": "object"
+    },
+    "tokens": {
+      "description": "The `tokens` field of the folded answer.",
+      "type": "object"
+    },
+    "ts": {
+      "description": "The `ts` field of the folded answer.",
+      "type": "object"
+    },
+    "type": {
+      "description": "The `type` field of the folded answer.",
+      "type": "object"
+    },
+    "unassessable_claims": {
+      "description": "The `unassessable_claims` field of the folded answer.",
+      "type": "object"
+    },
+    "upstream": {
+      "description": "The `upstream` field of the folded answer.",
+      "type": "object"
+    },
+    "verdict_meaning": {
+      "description": "The `verdict_meaning` field of the folded answer.",
+      "type": "object"
+    },
+    "weak_signal_edges": {
+      "description": "The `weak_signal_edges` field of the folded answer.",
+      "type": "object"
+    },
+    "weak_signals": {
+      "description": "The `weak_signals` field of the folded answer.",
+      "type": "object"
+    }
+  },
+  "type": "object"
+}

AddedOct 31, 2026

TDQS

B3.3/5.0

Behavior3/5

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 the notable behavioral fact of a $0.05 USDC price, valuable context. But the '44 fields including action, assessable' fragment is garbled and overlaps with the existing output schema rather than clarifying behavior.

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?

The description is short and the purpose sentence is front-loaded, which is good. But the second sentence is a run-on mixing routing advice with a confusing artifact ('an object with 44 fields including action, assessable'), which hurts readability rather than earning its place.

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?

The tool is simple (2 optional params, annotations present, output schema exists) so much is already covered. Yet the two parameters' meaning and the format/structure of 'claims' remain unexplained, and the pricing detail is the only added behavior, leaving the description merely adequate.

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 nominally 100%, hitting the baseline 3, but the property descriptions are only '[POST /v1/data/source-independence]' endpoint markers with no real semantics. Neither the description nor the schema explains what 'claims' should contain or how 'similarity_threshold' governs the check, so the description adds nothing here.

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?

First sentence states a specific verb and resource: 'Verify that a research claim set has more than one source.' That is clear and actionable. However, the tool's most obvious sibling, verify_source_independence, is never mentioned; instead the description contrasts with verify_business_screen, leaving differentiation against the closest alternative incomplete.

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 explicit routing guidance ('use it rather than `verify_business_screen` for research independence, not business screen'), which is real when-to-use direction. But it ignores verify_source_independence, the nearest sibling, so the agent is steered toward the wrong comparison and must infer the research-vs-source distinction itself.

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.