Synthex Forge — x402 Paid Agent Services

Extract Contract Terms

extract_contract_terms

Destructive

The obligations in a contract as structured, dated data. use it rather than extract_invoice_fields for contract terms, not invoice fields; an object with 53 fields including DISTRIBUTION, EMPLOYMENT. $1.5 USDC.

Input Schema

Name	Required	Description
`as_of`	No	The date the answer is computed as of (YYYY-MM-DD). Defaults to today. Use it to reproduce a past answer exactly.
`document_b64`	No	The document, base64-encoded, when the text is not available.
`jurisdiction`	No	The jurisdiction the answer applies to. Accepts an ISO-3166 alpha-2 code or a country name.
`document_text`	No	The document text to read.
`document_type`	No	The kind of document.

Output Schema

Name	Required	Description
`id`	No	The `id` field of the response.
`MSA`	No	The `MSA` field of the response.
`NDA`	No	The `NDA` field of the response.
`SaaS`	No	The `SaaS` field of the response.
`asOf`	No	The `asOf` field of the response.
`gaps`	No	The `gaps` field of the response.
`kind`	No	The `kind` field of the response.
`name`	No	The `name` field of the response.
`note`	No	A note on how the answer was produced.
`role`	No	The `role` field of the response.
`term`	No	The `term` field of the response.
`LEASE`	No	The `LEASE` field of the response.
`as_of`	No	The date the answer is computed as of.
`chars`	No	The `chars` field of the response.
`count`	No	The `count` field of the response.
`order`	No	The `order` field of the response.
`SUPPLY`	No	The `SUPPLY` field of the response.
`checks`	No	The individual checks that were run.
`clause`	No	The `clause` field of the response.
`detail`	Yes	Human-readable explanation of the verdict.
`expiry`	No	The `expiry` field of the response.
`sha256`	No	The `sha256` field of the response.
`source`	No	The `source` field of the response.
`status`	No	The status of the operation.
`parties`	No	The `parties` field of the response.
`coverage`	No	How much of the underlying corpus the answer is based on.
`signedBy`	No	The `signedBy` field of the response.
`effective`	No	The `effective` field of the response.
`liability`	No	The `liability` field of the response.
`signed_at`	No	The `signed_at` field of the response.
`stored_at`	No	The `stored_at` field of the response.
`EMPLOYMENT`	No	The `EMPLOYMENT` field of the response.
`commercial`	No	The `commercial` field of the response.
`ed25519Sig`	No	The `ed25519Sig` field of the response.
`extract_id`	No	The `extract_id` field of the response.
`ambiguities`	No	The `ambiguities` field of the response.
`termination`	No	The `termination` field of the response.
`DISTRIBUTION`	No	The `DISTRIBUTION` field of the response.
`documentType`	No	The `documentType` field of the response.
`evidenceCore`	No	The `evidenceCore` field of the response.
`jurisdiction`	No	The `jurisdiction` field of the response.
`document_type`	No	The `document_type` field of the response.
`governing_law`	No	The `governing_law` field of the response.
`documentDigest`	No	The `documentDigest` field of the response.
`document_chars`	No	The `document_chars` field of the response.
`groups_located`	No	The `groups_located` field of the response.
`profileVersion`	No	Version of the answer profile.
`why_unresolved`	No	The `why_unresolved` field of the response.
`document_digest`	No	The `document_digest` field of the response.
`groups_searched`	No	The `groups_searched` field of the response.
`profile_version`	No	Version of the answer profile.
`SERVICE_AGREEMENT`	No	The `SERVICE_AGREEMENT` field of the response.
`groups_not_located`	No	The `groups_not_located` field of the response.

Schema Changelog

Changes observed during successful MCP inspections.

Changed54 schema fields changedOct 31, 2026

addedOutput schema / properties / DISTRIBUTION

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

addedOutput schema / properties / EMPLOYMENT

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

addedOutput schema / properties / LEASE

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

addedOutput schema / properties / MSA

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

addedOutput schema / properties / NDA

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

addedOutput schema / properties / SERVICE_AGREEMENT

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

addedOutput schema / properties / SUPPLY

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

addedOutput schema / properties / SaaS

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

addedOutput schema / properties / ambiguities

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

addedOutput schema / properties / asOf

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

addedOutput schema / properties / as_of

Added value: +{
+  "description": "The date the answer is computed as of.",
+  "type": "string"
+}

addedOutput schema / properties / chars

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

addedOutput schema / properties / checks

Added value: +{
+  "description": "The individual checks that were run.",
+  "items": {
+    "description": "One record.",
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / clause

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

addedOutput schema / properties / commercial

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

addedOutput schema / properties / count

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

addedOutput schema / properties / coverage

Added value: +{
+  "description": "How much of the underlying corpus the answer is based on.",
+  "type": "object"
+}

addedOutput schema / properties / detail

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

addedOutput schema / properties / documentDigest

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

addedOutput schema / properties / documentType

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

addedOutput schema / properties / document_chars

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

addedOutput schema / properties / document_digest

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

addedOutput schema / properties / document_type

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

addedOutput schema / properties / ed25519Sig

Added value: +{
+  "description": "The `ed25519Sig` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / effective

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

addedOutput schema / properties / evidenceCore

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

addedOutput schema / properties / expiry

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

addedOutput schema / properties / extract_id

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

addedOutput schema / properties / gaps

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

addedOutput schema / properties / governing_law

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

addedOutput schema / properties / groups_located

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

addedOutput schema / properties / groups_not_located

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

addedOutput schema / properties / groups_searched

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

addedOutput schema / properties / id

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

addedOutput schema / properties / jurisdiction

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

addedOutput schema / properties / kind

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

addedOutput schema / properties / liability

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

addedOutput schema / properties / name

Added value: +{
+  "description": "The `name` 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 / order

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

addedOutput schema / properties / parties

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

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 / role

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

addedOutput schema / properties / sha256

Added value: +{
+  "description": "The `sha256` field of the response.",
+  "type": "object"
+}

addedOutput schema / properties / signedBy

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

addedOutput schema / properties / signed_at

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

addedOutput schema / properties / source

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

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

addedOutput schema / properties / stored_at

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

addedOutput schema / properties / term

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

addedOutput schema / properties / termination

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

addedOutput schema / properties / why_unresolved

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

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

AddedOct 31, 2026

TDQS

B3.3/5.0

Behavior3/5

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

The description adds one genuinely behavioral fact not present in structured fields: the call costs $1.5 USDC, which matters for an agent deciding whether to invoke it. Beyond that, it is silent. The annotations declare destructiveHint=true and readOnlyHint=false on what reads like an extraction operation, and the description never reconciles that, nor does it state what, if anything, is mutated or what happens when required document inputs are missing.

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?

It is short and the routing rule comes early, which is good. But the middle sentence is punctuated into incoherence, the 53-field enumeration with unattributed uppercase tokens is noise rather than signal, and both the field count and the trailing price are left as dangling fragments.

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?

With only five parameters, full schema coverage, and an output schema that carries the return shape, the definition does not need to re-explain results. The remaining gap is that a paid, destructively-annotated call gets no explanation of what the charge buys or what side effects occur, which the agent cannot learn from the schema alone.

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 all five parameters (`as_of`, `document_b64`, `jurisdiction`, `document_text`, `document_type`) are already fully documented with defaults and formats. The description only echoes this via "dated data." Baseline 3 applies when the schema carries the weight and the prose adds nothing further.

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 opening sentence, "The obligations in a contract as structured, dated data," is a noun phrase with no verb, so the agent must infer "extract" from the tool name rather than reading it. The named sibling contrast does help isolate it from invoice extraction, but "an object with 53 fields including DISTRIBUTION, EMPLOYMENT" is cryptic and reads more like leaked metadata than a purpose statement.

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?

It explicitly names `extract_invoice_fields` and states the selection rule: use this for contract terms, not invoice fields. That is a real routing instruction. However, other neighbouring extractors (`extract_invoice_text`, `extract_sec_filing`, `convert_document`) are not addressed, and there is no stated pre-condition such as requiring `document_text` or `document_b64` to be supplied.

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.