Synthex Forge — x402 Paid Agent Services

Get Agent Forensics

get_agent_forensics

Read-onlyIdempotent

Reconstruct what happened across a payment and its workflow. use it rather than get_agent_memory for agent forensics, not agent memory; an object with 8 fields including evidence, exception. $0.25 USDC.

Input Schema

Name	Required	Description
`evidence`	No	The evidence supporting the claim, as a list of named documents or URLs.
`expected`	No	The expected this operation operates on. See the schema for its type and whether it is required.
`requestId`	No	A caller-supplied idempotency key. The same key returns the same result instead of charging twice.
`payment_ref`	No	The payment reference the operation concerns.
`workflow_id`	No	The identifier of the workflow.
`generated_at`	No	The generated at this operation operates on. See the schema for its type and whether it is required.

Output Schema

Name	Required	Description
`evidence`	No	The `evidence` field of the response.
`expected`	No	The `expected` field of the response.
`problems`	No	The `problems` field of the response.
`exception`	No	The `exception` field of the response.
`request_id`	No	The `request_id` field of the response.
`payment_ref`	No	The `payment_ref` field of the response.
`workflow_id`	No	The `workflow_id` field of the response.
`generated_at`	No	The `generated_at` field of the response.

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedOct 31, 2026

addedOutput schema / properties / evidence

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

addedOutput schema / properties / exception

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

addedOutput schema / properties / expected

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

addedOutput schema / properties / generated_at

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

addedOutput schema / properties / payment_ref

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

addedOutput schema / properties / problems

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

addedOutput schema / properties / request_id

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

removedOutput schema / properties / status

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

addedOutput schema / properties / workflow_id

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

AddedOct 31, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds the genuinely useful disclosure that each call costs $0.25 USDC and returns an object of 8 fields including `evidence` and `exception`. It says nothing about latency, billing on failure, or whether a partial reconstruction is possible, which matters for a paid read.

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?

Two sentences that are broken by an internal semicolon, a mid-sentence lowercase 'use', and a fragment ending ('an object with 8 fields including evidence, exception. $0.25 USDC.'). The key routing constraint and the price are buried rather than front-loaded, and the return-shape fragment duplicates the output schema.

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 annotations, a full output schema and 100% schema coverage, most structured context is already present, and the description supplies cost plus a sibling distinction. It is still thin on the operational semantics of a paid forensic reconstruction — what inputs are minimally sufficient, and what 'across a payment and its workflow' yields when only one of the two ids is supplied.

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 the six parameters (evidence, expected, requestId, payment_ref, workflow_id, generated_at) are already documented individually, including the idempotency-key semantics of requestId. The description adds no parameter-level meaning, so the 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?

States a specific verb and scope: 'Reconstruct what happened across a payment and its workflow', and explicitly names the sibling `get_agent_memory` as the thing it is not. The purpose is clear despite awkward phrasing, but the clause 'for agent forensics, not agent memory' is redundant with the tool name and adds noise rather than precision.

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 route the agent away from `get_agent_memory`, which is real guidance, and the $0.25 USDC price helps a cost-sensitive agent decide. However it never states when forensics reconstruction is actually warranted (disputes? failures? audits?) and offers no other alternatives such as `search_forensics_evidence` or `recover_agent_workflow`, which are equally plausible siblings.

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.