Synthex Forge — x402 Paid Agent Services

Get Output Preflight

get_output_preflight

Read-onlyIdempotent

deterministic shape preflight (L1 schema-shape + L4 evidence-shape. use it rather than verify_tool_output for preflight, not output; an object with 32 fields including assessable, axis.

Input Schema

Name	Required	Description
`output`	Yes	Must not be null. The handler rejects a null value with 400 `bad_request`.
`schema`	No	The JSON Schema the operation operates on.
`claimed`	No	The claim being made.
`subject`	No	The subject the operation is applied to — an id, a URL or a name, depending on the operation.

Output Schema

Name	Required	Description
`ok`	Yes	Whether the operation succeeded.
`axis`	No	The `axis` field of the response.
`note`	No	A note on how the answer was produced.
`path`	No	The `path` field of the response.
`shape`	No	The `shape` field of the response.
`total`	No	The `total` field of the response.
`clause`	No	The `clause` field of the response.
`counts`	No	The `counts` field of the response.
`detail`	Yes	Human-readable explanation of the verdict.
`reason`	No	Why the verdict was reached.
`schema`	No	The `schema` field of the response.
`usable`	No	The `usable` field of the response.
`finding`	No	The `finding` field of the response.
`scoping`	No	The `scoping` field of the response.
`skipped`	No	The `skipped` field of the response.
`subject`	No	The `subject` field of the response.
`verdict`	Yes	The decision this tool returned.
`evidence`	No	The `evidence` field of the response.
`failures`	No	The `failures` field of the response.
`findings`	No	The `findings` field of the response.
`severity`	No	The `severity` field of the response.
`assessable`	No	The `assessable` field of the response.
`violations`	No	The `violations` field of the response.
`output_kind`	No	The `output_kind` field of the response.
`observations`	No	The `observations` field of the response.
`coverage_gaps`	No	The `coverage_gaps` field of the response.
`hash_bound_ok`	No	The `hash_bound_ok` field of the response.
`output_length`	No	The `output_length` field of the response.
`output_present`	No	The `output_present` field of the response.
`hash_bound_fail`	No	The `hash_bound_fail` field of the response.
`output_top_keys`	No	The `output_top_keys` field of the response.
`unenforced_schema_keywords`	No	The `unenforced_schema_keywords` field of the response.

Schema Changelog

Changes observed during successful MCP inspections.

Changed34 schema fields changedOct 31, 2026

addedOutput schema / properties / assessable

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

addedOutput schema / properties / axis

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

addedOutput schema / properties / clause

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

addedOutput schema / properties / counts

Added value: +{
+  "description": "The `counts` 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 / detail

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

addedOutput schema / properties / evidence

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

addedOutput schema / properties / failures

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

addedOutput schema / properties / finding

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

addedOutput schema / properties / findings

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

addedOutput schema / properties / hash_bound_fail

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

addedOutput schema / properties / hash_bound_ok

Added value: +{
+  "description": "The `hash_bound_ok` 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 / observations

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

addedOutput schema / properties / ok

Added value: +{
+  "description": "Whether the operation succeeded.",
+  "type": "boolean"
+}

addedOutput schema / properties / output_kind

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

addedOutput schema / properties / output_length

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

addedOutput schema / properties / output_present

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

addedOutput schema / properties / output_top_keys

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

addedOutput schema / properties / path

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

addedOutput schema / properties / reason

Added value: +{
+  "description": "Why the verdict was reached.",
+  "type": "string"
+}

addedOutput schema / properties / schema

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

addedOutput schema / properties / scoping

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

addedOutput schema / properties / severity

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

addedOutput schema / properties / shape

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

addedOutput schema / properties / skipped

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

removedOutput schema / properties / status

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

addedOutput schema / properties / subject

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

addedOutput schema / properties / total

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

addedOutput schema / properties / unenforced_schema_keywords

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

addedOutput schema / properties / usable

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

addedOutput schema / properties / verdict

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

addedOutput schema / properties / violations

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

addedOutput schema / required

Added value: +[
+  "detail",
+  "ok",
+  "verdict"
+]

AddedOct 31, 2026

TDQS

B3.1/5.0

Behavior3/5

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

Annotations already cover read-only, idempotent, non-destructive, and closed-world behavior. The description adds 'deterministic' and clarifies this is preflight rather than output verification, which is useful behavioral context. The '32 fields including assessable, axis' detail is redundant with the output schema and adds no behavioral insight.

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 is a fragmented run-on with an unclosed parenthesis and three poorly connected clauses. The return-shape detail ('an object with 32 fields...') is redundant given the output schema and crowds out what should be the front-loaded purpose statement.

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?

The output schema covers return values and annotations cover safety, so the description needn't repeat those. However, for a tool whose name and jargon ('L1/L4', 'evidence-shape') are opaque, the description is thin on what the preflight actually validates and when it would fail, leaving gaps an agent must infer.

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 input schema already explains the output, schema, claimed, and subject parameters. The description does not add any meaning about parameter usage or interactions, leaving the schema to do all the work.

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?

It says this is a 'deterministic shape preflight' and distinguishes it from verify_tool_output, which helps. But the core purpose is obscured by jargon ('L1 schema-shape + L4 evidence-shape') and it never plainly states what is being preflighted or what a passing/failing shape means.

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?

The phrase 'use it rather than `verify_tool_output` for preflight, not output' explicitly routes the agent to this tool for preflight checks and away from the sibling for output verification. The alternative and its condition are named, though no further exclusions are given.

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.