Synthex Forge — x402 Paid Agent Services

Verify Agent Delegation

verify_agent_delegation

Read-onlyIdempotent

Delegating work to an agent that cannot do it. use it rather than verify_digital_deliverable for agent delegation, not digital deliverable; an object with 24 fields including BLOCKED, INDETERMINATE. $0.25 USDC.

Input Schema

Name	Required	Description	Default
`preflight.manifest`	No	[POST /v1/agent/preflight]
`preflight.requestId`	No	[POST /v1/agent/preflight]

Output Schema

Name	Required	Description
`ok`	No	Whether every inner call succeeded.
`READY`	No	The `READY` field of the folded answer.
`field`	No	The `field` field of the folded answer.
`BLOCKED`	No	The `BLOCKED` field of the folded answer.
`reasons`	No	The `reasons` field of the folded answer.
`results`	No	One result per inner call.
`summary`	No	One-line summary of the folded answer.
`verdict`	No	The `verdict` field of the folded answer.
`problems`	No	The `problems` field of the folded answer.
`exception`	No	The `exception` field of the folded answer.
`checks_run`	No	The `checks_run` field of the folded answer.
`request_id`	No	The `request_id` field of the folded answer.
`risk_flags`	No	The `risk_flags` field of the folded answer.
`price_factor`	No	The `price_factor` field of the folded answer.
`INDETERMINATE`	No	The `INDETERMINATE` field of the folded answer.
`coverage_gaps`	No	The `coverage_gaps` field of the folded answer.
`price_max_usd`	No	The `price_max_usd` field of the folded answer.
`price_min_usd`	No	The `price_min_usd` field of the folded answer.
`uptime_pct_30d`	No	The `uptime_pct_30d` field of the folded answer.
`checks_requested`	No	The `checks_requested` field of the folded answer.
`observation_count`	No	The `observation_count` field of the folded answer.
`price_changed_30d`	No	The `price_changed_30d` field of the folded answer.
`READY_WITH_WARNINGS`	No	The `READY_WITH_WARNINGS` field of the folded answer.
`consecutive_failures`	No	The `consecutive_failures` 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": {
+    "BLOCKED": {
+      "description": "The `BLOCKED` field of the folded answer.",
+      "type": "object"
+    },
+    "INDETERMINATE": {
+      "description": "The `INDETERMINATE` field of the folded answer.",
+      "type": "object"
+    },
+    "READY": {
+      "description": "The `READY` field of the folded answer.",
+      "type": "object"
+    },
+    "READY_WITH_WARNINGS": {
+      "description": "The `READY_WITH_WARNINGS` field of the folded answer.",
+      "type": "object"
+    },
+    "checks_requested": {
+      "description": "The `checks_requested` field of the folded answer.",
+      "type": "object"
+    },
+    "checks_run": {
+      "description": "The `checks_run` field of the folded answer.",
+      "type": "object"
+    },
+    "consecutive_failures": {
+      "description": "The `consecutive_failures` field of the folded answer.",
+      "type": "object"
+    },
+    "coverage_gaps": {
+      "description": "The `coverage_gaps` field of the folded answer.",
+      "type": "object"
+    },
+    "exception": {
+      "description": "The `exception` field of the folded answer.",
+      "type": "object"
+    },
+    "field": {
+      "description": "The `field` field of the folded answer.",
+      "type": "object"
+    },
+    "observation_count": {
+      "description": "The `observation_count` field of the folded answer.",
+      "type": "object"
+    },
+    "ok": {
+      "description": "Whether every inner call succeeded.",
+      "type": "boolean"
+    },
+    "price_changed_30d": {
+      "description": "The `price_changed_30d` field of the folded answer.",
+      "type": "object"
+    },
+    "price_factor": {
+      "description": "The `price_factor` field of the folded answer.",
+      "type": "object"
+    },
+    "price_max_usd": {
+      "description": "The `price_max_usd` field of the folded answer.",
+      "type": "object"
+    },
+    "price_min_usd": {
+      "description": "The `price_min_usd` field of the folded answer.",
+      "type": "object"
+    },
+    "problems": {
+      "description": "The `problems` field of the folded answer.",
+      "type": "object"
+    },
+    "reasons": {
+      "description": "The `reasons` field of the folded answer.",
+      "type": "object"
+    },
+    "request_id": {
+      "description": "The `request_id` field of the folded answer.",
+      "type": "object"
+    },
+    "results": {
+      "description": "One result per inner call.",
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "risk_flags": {
+      "description": "The `risk_flags` field of the folded answer.",
+      "type": "object"
+    },
+    "summary": {
+      "description": "One-line summary of the folded answer.",
+      "type": "string"
+    },
+    "uptime_pct_30d": {
+      "description": "The `uptime_pct_30d` field of the folded answer.",
+      "type": "object"
+    },
+    "verdict": {
+      "description": "The `verdict` field of the folded answer.",
+      "type": "object"
+    }
+  },
+  "type": "object"
+}

AddedOct 31, 2026

TDQS

C2.7/5.0

Behavior3/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's main added value is the pricing disclosure '$0.25 USDC' and the hint that results include BLOCKED/INDETERMINATE states. It omits what input the manifest must contain and under what conditions a BLOCKED verdict is produced.

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

Conciseness2/5

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

The text is a run-on of fragments separated by semicolons and periods, with no front-loaded statement of purpose and a sentence fragment leading. Length is short, but the structure actively impedes parsing rather than being economical.

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

Completeness2/5

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

An output schema exists so return shapes needn't be explained, but for a paid verification call with a free-form manifest parameter and no required fields, the description should clarify what the manifest must declare and when the verdict is BLOCKED. Neither is addressed, so an agent cannot confidently construct a call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Both parameters carry 'schema descriptions' that are only endpoint paths ('[POST /v1/agent/preflight]'), which convey no meaning about what `preflight.manifest` should contain or what `preflight.requestId` is for. The description does not compensate at all, leaving the only substantive parameter effectively undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description implies the tool verifies agent delegation, but the leading fragment 'Delegating work to an agent that cannot do it' is a dangling clause with no main verb, making the actual action ambiguous. A reader can infer the resource (agent delegation) but not clearly what operation is performed on it.

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?

It does name a concrete alternative ('use it rather than `verify_digital_deliverable` for agent delegation, not digital deliverable'), which is genuinely useful routing signal. However the clause is grammatically tangled and gives no when-not conditions, prerequisites, or failure-mode guidance beyond the sibling contrast.

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.