Synthex Forge — x402 Paid Agent Services

Run Agent

run_agent

Read-onlyIdempotent

One audited agent execution with a cost ledger and a signed. use it rather than get_agent_forensics for agent, not agent forensics; an object with 35 fields including Authorization, Content-Type. $1 USDC.

Input Schema

Name	Required	Description	Default
`task`	Yes	The task this operation operates on. See the schema for its type and whether it is required.
`context`	No	Free-form context the operation needs but does not model as a structured field.

Output Schema

Name	Required	Description
`ts`	No	The `ts` field of the response.
`note`	No	A note on how the answer was produced.
`role`	No	The `role` field of the response.
`error`	No	The machine-readable error code, when the operation failed.
`model`	No	The `model` field of the response.
`usage`	No	The `usage` field of the response.
`budget`	No	The `budget` field of the response.
`detail`	Yes	Human-readable explanation of the verdict.
`result`	No	The `result` field of the response.
`run_id`	No	The `run_id` field of the response.
`signer`	No	The `signer` field of the response.
`stream`	No	The `stream` field of the response.
`content`	No	The `content` field of the response.
`options`	No	The `options` field of the response.
`receipt`	No	The `receipt` field of the response.
`wall_ms`	No	The `wall_ms` field of the response.
`messages`	No	The `messages` field of the response.
`task_hash`	No	The `task_hash` field of the response.
`verify_at`	No	The `verify_at` field of the response.
`resetAtUtc`	No	The `resetAtUtc` field of the response.
`tool_calls`	No	The `tool_calls` field of the response.
`num_predict`	No	The `num_predict` field of the response.
`result_hash`	No	The `result_hash` field of the response.
`temperature`	No	The `temperature` field of the response.
`Content-Type`	No	The `Content-Type` field of the response.
`jobsRunToday`	No	The `jobsRunToday` field of the response.
`Authorization`	No	The `Authorization` field of the response.
`prompt_tokens`	No	The `prompt_tokens` field of the response.
`receipt_sha256`	No	The `receipt_sha256` field of the response.
`stopped_reason`	No	The `stopped_reason` field of the response.
`completion_tokens`	No	The `completion_tokens` field of the response.
`cost_usd_estimate`	No	The `cost_usd_estimate` field of the response.
`receipt_signature`	No	The `receipt_signature` field of the response.
`result_hash_check`	No	The `result_hash_check` field of the response.
`retryAfterSeconds`	No	The `retryAfterSeconds` field of the response.

Schema Changelog

Changes observed during successful MCP inspections.

Changed37 schema fields changedOct 31, 2026

addedOutput schema / properties / Authorization

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

addedOutput schema / properties / Content-Type

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

addedOutput schema / properties / budget

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

addedOutput schema / properties / completion_tokens

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

addedOutput schema / properties / content

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

addedOutput schema / properties / cost_usd_estimate

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

addedOutput schema / properties / detail

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

addedOutput schema / properties / error

Added value: +{
+  "description": "The machine-readable error code, when the operation failed.",
+  "type": "string"
+}

addedOutput schema / properties / jobsRunToday

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

addedOutput schema / properties / messages

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

addedOutput schema / properties / model

Added value: +{
+  "description": "The `model` 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 / num_predict

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

addedOutput schema / properties / options

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

addedOutput schema / properties / prompt_tokens

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

addedOutput schema / properties / receipt

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

addedOutput schema / properties / receipt_sha256

Added value: +{
+  "description": "The `receipt_sha256` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / receipt_signature

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

addedOutput schema / properties / resetAtUtc

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

addedOutput schema / properties / result

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

addedOutput schema / properties / result_hash

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

addedOutput schema / properties / result_hash_check

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

addedOutput schema / properties / retryAfterSeconds

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

addedOutput schema / properties / role

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

addedOutput schema / properties / run_id

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

addedOutput schema / properties / signer

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

removedOutput schema / properties / status

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

addedOutput schema / properties / stopped_reason

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

addedOutput schema / properties / stream

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

addedOutput schema / properties / task_hash

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

addedOutput schema / properties / temperature

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

addedOutput schema / properties / tool_calls

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

addedOutput schema / properties / ts

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

addedOutput schema / properties / usage

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

addedOutput schema / properties / verify_at

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

addedOutput schema / properties / wall_ms

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

addedOutput schema / required
```
Added value: +[
+  "detail"
+]
```

AddedOct 31, 2026

TDQS

C2.4/5.0

Behavior1/5

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

The annotations declare readOnlyHint=true and destructiveHint=false, but the description says this performs an agent execution with a cost ledger and a $1 USDC charge. Executing an agent and charging money are side effects, directly contradicting the read-only annotation.

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 description is short but poorly structured: sentence fragments ('a signed.'), an out-of-place return-object detail ('including Authorization, Content-Type'), and unclear punctuation obscure the message rather than front-loading the key purpose.

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?

The tool has an output schema, so return values need less explanation, but the description still leaves critical behavior opaque: what 'signed' refers to, what the audited execution actually does, and how the $1 USDC charge is applied. For an execution tool with side effects, this is insufficient.

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 both parameters are documented in the schema. The description adds no parameter-specific meaning beyond the schema, which is acceptable at baseline 3.

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 gives a rough verb+resource ('audited agent execution') but is grammatically broken ('a signed.'), leaving the deliverable unclear. It tries to distinguish from get_agent_forensics, but the phrasing 'for agent, not agent forensics' is confusing rather than clarifying.

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 names an alternative ('use it rather than get_agent_forensics'), which is a genuine usage cue. However, the condition is garbled ('for agent, not agent forensics') and no explicit when-not-to-use guidance is provided.

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.