Synthex Forge — x402 Paid Agent Services

Settle A2A Escrow

settle_a2a_escrow

Destructive

Adjudicate what one agent owes another. use it rather than create_a2a_escrow for a2a escrow specifically; an object with 26 fields including amount_due_usd, amount_usd. $0.25 USDC.

Input Schema

Name	Required	Description
`task`	No	The task this operation operates on. See the schema for its type and whether it is required.
`payee`	No	The payee this operation operates on. See the schema for its type and whether it is required.
`payer`	No	The payer this operation operates on. See the schema for its type and whether it is required.
`acceptance`	No	The acceptance this operation operates on. See the schema for its type and whether it is required.
`amount_usd`	No	The amount in USD. The settlement rail converts it to the exact atomic amount.
`completion_evidence`	No	The completion evidence this operation operates on. See the schema for its type and whether it is required.

Output Schema

Name	Required	Description
`to`	No	The `to` field of the response.
`from`	No	The `from` field of the response.
`kind`	No	The `kind` field of the response.
`note`	No	A note on how the answer was produced.
`basis`	No	The `basis` field of the response.
`counts`	No	The `counts` field of the response.
`verdict`	Yes	The decision this tool returned.
`evidence`	No	The `evidence` field of the response.
`executed`	No	The `executed` field of the response.
`signature`	Yes	The Ed25519 signature over the evidence core, base64-encoded.
`signed_by`	No	The key id that signed the answer.
`amount_usd`	No	The amount the operation concerned.
`evidence_core`	Yes	The canonical, signed core of the answer — the payload the signature covers.
`output_sha256`	Yes	SHA-256 hex digest of the canonical evidence core.
`scopeBoundary`	No	The `scopeBoundary` field of the response.
`amount_due_usd`	No	The `amount_due_usd` field of the response.
`evidence_count`	No	The `evidence_count` field of the response.
`missing_fields`	No	The `missing_fields` field of the response.
`profileVersion`	No	Version of the answer profile.
`scope_boundary`	No	What this service explicitly does not do.
`dispute_reasons`	No	The `dispute_reasons` field of the response.
`profile_version`	No	Version of the answer profile.
`canonicalization`	No	The canonicalisation rule the digest was computed under.
`methodologyVersion`	No	The `methodologyVersion` field of the response.
`methodology_version`	No	Version of the method that produced the answer.
`settlement_instruction`	No	The `settlement_instruction` field of the response.

Schema Changelog

Changes observed during successful MCP inspections.

Changed28 schema fields changedOct 31, 2026

addedOutput schema / properties / amount_due_usd

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

addedOutput schema / properties / amount_usd

Added value: +{
+  "description": "The amount the operation concerned.",
+  "type": "number"
+}

addedOutput schema / properties / basis

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

addedOutput schema / properties / canonicalization

Added value: +{
+  "description": "The canonicalisation rule the digest was computed under.",
+  "type": "string"
+}

addedOutput schema / properties / counts

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

addedOutput schema / properties / dispute_reasons

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

addedOutput schema / properties / evidence

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

addedOutput schema / properties / evidence_core

Added value: +{
+  "description": "The canonical, signed core of the answer — the payload the signature covers.",
+  "type": "object"
+}

addedOutput schema / properties / evidence_count

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

addedOutput schema / properties / executed

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

addedOutput schema / properties / from

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

addedOutput schema / properties / kind

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

addedOutput schema / properties / methodologyVersion

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

addedOutput schema / properties / methodology_version

Added value: +{
+  "description": "Version of the method that produced the answer.",
+  "type": "string"
+}

addedOutput schema / properties / missing_fields

Added value: +{
+  "description": "The `missing_fields` 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 / output_sha256

Added value: +{
+  "description": "SHA-256 hex digest of the canonical evidence core.",
+  "type": "string"
+}

addedOutput schema / properties / profileVersion

Added value: +{
+  "description": "Version of the answer profile.",
+  "type": "string"
+}

addedOutput schema / properties / profile_version

Added value: +{
+  "description": "Version of the answer profile.",
+  "type": "string"
+}

addedOutput schema / properties / scopeBoundary

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

addedOutput schema / properties / scope_boundary

Added value: +{
+  "description": "What this service explicitly does not do.",
+  "type": "string"
+}

addedOutput schema / properties / settlement_instruction

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

addedOutput schema / properties / signature

Added value: +{
+  "description": "The Ed25519 signature over the evidence core, base64-encoded.",
+  "type": "string"
+}

addedOutput schema / properties / signed_by

Added value: +{
+  "description": "The key id that signed the answer.",
+  "type": "string"
+}

removedOutput schema / properties / status

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

addedOutput schema / properties / to

Added value: +{
+  "description": "The `to` 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: +[
+  "evidence_core",
+  "output_sha256",
+  "signature",
+  "verdict"
+]

AddedOct 31, 2026

TDQS

C2.4/5.0

Behavior2/5

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

Annotations already declare destructiveHint=true and idempotentHint=false, so the agent knows this is a consequential write. The description adds the $0.25 USDC cost, which is useful, but gives no warning about irreversibility, what funds/state get destroyed, or required authorization despite the destructive flag.

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 reads as concatenated fragments ('...escrow specifically; an object with 26 fields... $0.25 USDC') rather than a front-loaded, coherent sentence. The '$0.25 USDC' fragment is cryptic and disconnected, so it is under-structured rather than truly concise.

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 values needn't be explained, but a destructive, non-idempotent settlement tool with 0 required params needs far more about preconditions, consequences, and required fields. The description leaves the agent without enough to invoke it safely.

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 schema already documents the six parameters; baseline is 3. The description's mention of 'amount_usd' adds nothing the schema doesn't, and 'amount_due_usd' appears to reference output fields rather than inputs.

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 verb 'Adjudicate' is specific and 'what one agent owes another' gestures at settlement, but the description never plainly states that this settles an A2A escrow (the title carries that load). The purpose is inferable but vague on the actual mechanism, and the sibling reference is muddled 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 Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The clause 'use it rather than create_a2a_escrow' is present but misleading: creating and settling an escrow are different lifecycle stages, not interchangeable alternatives. No real when-to-use or precondition guidance is given, so an agent could easily pick the wrong tool.

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.