Synthex Forge — x402 Paid Agent Services

Get Agent Preflight

get_agent_preflight

Read-onlyIdempotent

Is this agent workflow ready to execute?. use it rather than get_agent_forensics for agent preflight, not agent forensics; an object with 21 fields including BLOCKED, INDETERMINATE. $0.25 USDC.

Input Schema

Name	Required	Description	Default
`manifest`	No	The manifest describing the delivered or expected artifact.
`requestId`	No	A caller-supplied idempotency key. The same key returns the same result instead of charging twice.

Output Schema

Name	Required	Description
`READY`	No	The `READY` field of the response.
`field`	No	The `field` field of the response.
`BLOCKED`	No	The `BLOCKED` field of the response.
`reasons`	No	The `reasons` field of the response.
`verdict`	Yes	The decision this tool returned.
`problems`	No	The `problems` field of the response.
`exception`	No	The `exception` field of the response.
`checks_run`	No	The `checks_run` field of the response.
`request_id`	No	The `request_id` field of the response.
`risk_flags`	No	The `risk_flags` field of the response.
`price_factor`	No	The `price_factor` field of the response.
`INDETERMINATE`	No	The `INDETERMINATE` field of the response.
`coverage_gaps`	No	The `coverage_gaps` field of the response.
`price_max_usd`	No	The `price_max_usd` field of the response.
`price_min_usd`	No	The `price_min_usd` field of the response.
`uptime_pct_30d`	No	The `uptime_pct_30d` field of the response.
`checks_requested`	No	The `checks_requested` field of the response.
`observation_count`	No	The `observation_count` field of the response.
`price_changed_30d`	No	The `price_changed_30d` field of the response.
`READY_WITH_WARNINGS`	No	The `READY_WITH_WARNINGS` field of the response.
`consecutive_failures`	No	The `consecutive_failures` field of the response.

Schema Changelog

Changes observed during successful MCP inspections.

Changed23 schema fields changedOct 31, 2026

addedOutput schema / properties / BLOCKED

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

addedOutput schema / properties / INDETERMINATE

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

addedOutput schema / properties / READY

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

addedOutput schema / properties / READY_WITH_WARNINGS

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

addedOutput schema / properties / checks_requested

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

addedOutput schema / properties / checks_run

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

addedOutput schema / properties / consecutive_failures

Added value: +{
+  "description": "The `consecutive_failures` 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 / exception

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

addedOutput schema / properties / field

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

addedOutput schema / properties / observation_count

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

addedOutput schema / properties / price_changed_30d

Added value: +{
+  "description": "The `price_changed_30d` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / price_factor

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

addedOutput schema / properties / price_max_usd

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

addedOutput schema / properties / price_min_usd

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

addedOutput schema / properties / problems

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

addedOutput schema / properties / reasons

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

addedOutput schema / properties / request_id

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

addedOutput schema / properties / risk_flags

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

removedOutput schema / properties / status

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

addedOutput schema / properties / uptime_pct_30d

Added value: +{
+  "description": "The `uptime_pct_30d` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / verdict

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

addedOutput schema / required
```
Added value: +[
+  "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 readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds pricing ("$0.25 USDC"), which the annotations and schema do not state except obliquely through the requestId double-charge note; that is a real behavioural fact an agent should know before calling. The mention of the 21-field response with BLOCKED/INDETERMINATE verdicts adds a little more context on outcomes.

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 and front-loads the core question, which is good. But the clause "use it rather than `get_agent_forensics` for agent preflight, not agent forensics" is repetitious, and "?." plus the fragment "an object with 21 fields..." make it read as stitched-together notes rather than a clean sentence.

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?

With an output schema present, return values need not be explained, and annotations carry the safety profile, so the remaining burden is light. Still, the description never says what a "preflight" checks against — the manifest contract is only defined in the schema — leaving the agent to infer what input quality determines a BLOCKED versus INDETERMINATE result.

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 both `manifest` and `requestId` are documented, including the idempotency/double-charge semantics. The description adds nothing about what a valid manifest looks like or what the 0-required-parameter behaviour means, so it neither compensates for nor duplicates the schema meaningfully. Baseline 3 applies.

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 frames a concrete readiness question ("Is this agent workflow ready to execute?") and names the verdict states it returns (BLOCKED, INDETERMINATE), so the resource and the kind of answer are both inferable. It also explicitly distinguishes itself from `get_agent_forensics`, so an agent can separate the two without reading both schemas. It is not phrased as a crisp verb+resource statement, which is why it is not a 5.

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 gives a direct routing rule: prefer this over `get_agent_forensics` for preflight rather than forensics, which is exactly the kind of disambiguation that helps selection. However, it ignores the crowded preflight family around it (`get_budget_preflight`, `get_output_preflight`, `get_quota_preflight`, `get_counterparty_preflight`), so the boundary in that direction is left to inference.

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.