Synthex Forge — x402 Paid Agent Services

Evaluate Deliverable Acceptance

evaluate_deliverable_acceptance

Read-onlyIdempotent

Check a delivered manifest against a specification. use it rather than accept_task_deliverable for deliverable acceptance, not task deliverable; an object with 23 fields including action, actual. $0.25 USDC.

Input Schema

Name	Required	Description	Default
`spec`	No	The spec this operation operates on. See the schema for its type and whether it is required.
`manifest`	No	The manifest describing the delivered or expected artifact.

Output Schema

Name	Required	Description
`id`	No	The `id` field of the response.
`fail`	No	The `fail` field of the response.
`pass`	No	The `pass` field of the response.
`type`	No	The `type` field of the response.
`score`	No	The numeric score this tool returned.
`total`	No	The `total` field of the response.
`action`	No	The `action` field of the response.
`actual`	No	The `actual` field of the response.
`counts`	No	The `counts` field of the response.
`detail`	Yes	Human-readable explanation of the verdict.
`status`	No	The status of the operation.
`checked`	No	The `checked` field of the response.
`artifact`	No	The `artifact` 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.
`dimensions`	No	The `dimensions` field of the response.
`requirements`	No	The `requirements` field of the response.
`undetermined`	No	The `undetermined` field of the response.
`extra_artifacts`	No	The `extra_artifacts` field of the response.
`verdict_meaning`	No	The `verdict_meaning` field of the response.
`requirement_count`	No	The `requirement_count` field of the response.
`dimensions_checked`	No	The `dimensions_checked` field of the response.

Schema Changelog

Changes observed during successful MCP inspections.

Changed24 schema fields changedOct 31, 2026

addedOutput schema / properties / action

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

addedOutput schema / properties / actual

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

addedOutput schema / properties / artifact

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

addedOutput schema / properties / checked

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

addedOutput schema / properties / counts

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

addedOutput schema / properties / detail

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

addedOutput schema / properties / dimensions

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

addedOutput schema / properties / dimensions_checked

Added value: +{
+  "description": "The `dimensions_checked` 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 / extra_artifacts

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

addedOutput schema / properties / fail

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

addedOutput schema / properties / id

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

addedOutput schema / properties / pass

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

addedOutput schema / properties / problems

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

addedOutput schema / properties / requirement_count

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

addedOutput schema / properties / requirements

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

addedOutput schema / properties / score

Added value: +{
+  "description": "The numeric score this tool returned.",
+  "type": "number"
+}

addedOutput schema / properties / status / description
```
Added value: +"The status of the operation."
```

addedOutput schema / properties / total

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

addedOutput schema / properties / type

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

addedOutput schema / properties / undetermined

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

addedOutput schema / properties / verdict_meaning

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

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

AddedOct 31, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already cover readOnly, idempotent, non-destructive, closed-world. The description adds useful context annotations do not: the $0.25 USDC cost and a hint about the response shape (object with 23 fields including action, actual). That extra cost/return context is genuine value beyond structured fields.

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?

Reasonably short, but the sentences are disorganized—the sibling differentiation sits mid-stream and the '23 fields including action, actual' fragment is ambiguous and reads like leftover output detail rather than clean guidance.

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

Completeness4/5

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 fully explained, and the annotations carry the safety profile. The description adds the cost and sibling routing, leaving little an agent critically needs missing, though the undefined 'action/actual' fields reduce clarity.

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 both spec and manifest. The description references checking a manifest against a specification but adds no format or validation syntax beyond the schema, so 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 (check) and resource (delivered manifest against a specification), and explicitly distinguishes itself from the accept_task_deliverable sibling. However, the trailing fragment 'an object with 23 fields including action, actual' muddles the purpose statement slightly.

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?

Explicitly names the alternative (accept_task_deliverable) and states the selection condition: use this for deliverable acceptance, not task deliverable. Clear routing, though the phrasing is awkward and gradable.

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.