Agent Revenue Network

by dev.workers.nadirventurelabs.agent-revenue-network

AI Agent Job Contract with Objective Acceptance Criteria · Compiler

job_contract_compile

Read-onlyIdempotent

Compile an AI agent job contract with objective acceptance criteria into ARN's deterministic canonical job-contract format. Supply a goal, deliverables and one or more supported machine-checkable criteria: bounded JSON Schema, exact JSON value, required or forbidden text, or SHA-256. Paid execution rejects ambiguous and unsupported fields, canonicalizes the contract and returns a SHA-256 contract hash. It does not claim work, execute it or move funds. Pair the result with execution_proof_pack after delivery. This free MCP discovery call does not execute the advertised capability and does not charge; it returns the exact x402 endpoint, price and payment guide for execution.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "goal": "<goal>",
      "deliverables": "<deliverables>",
      "acceptanceCriteria": "<acceptanceCriteria>"
    },
    "name": "job_contract_compile"
  }
}

Input Schema

Name	Required	Description
`goal`	Yes	Concrete outcome the worker must deliver.
`jobId`	No	Optional external job identifier.
`rights`	No	Declared ownership or licence arrangement; not a legal opinion.
`payment`	No	Optional agreed amount and uppercase currency code; no payment is initiated.
`deadline`	No	Optional ISO 8601 delivery deadline; runtime parsing fails closed.
`capabilities`	No	Skills required to perform the work.
`deliverables`	Yes	Named files or outputs expected from the work.
`acceptanceCriteria`	Yes	Objective checks ARN can later perform against named artifacts.
`dataClassification`	No	Sensitivity label applied to the job inputs and outputs.

Output Schema

Name	Required	Description
`price`	Yes
`method`	Yes	HTTP method for paid execution.
`endpoint`	Yes	Canonical absolute ARN HTTP URL to POST the same tool arguments to for paid execution.
`protocol`	Yes	Payment protocol required by the HTTP execution endpoint.
`instruction`	Yes	How to execute the capability after receiving the payment requirement.
`paymentGuide`	Yes	Public setup guide with a working x402 v2 Base-mainnet client example.
`paymentRequired`	Yes	Always true for paid ARN capabilities exposed over MCP.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 1, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Goes well beyond the annotations: it describes canonicalization behavior, that unsupported keywords fail closed, that a SHA-256 contract hash is returned, and that this specific MCP call is a free discovery call returning the x402 endpoint, price and payment guide rather than executing. This resolves the tension between 'compile' and readOnlyHint=true cleanly.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Core purpose and constraints are front-loaded, and the when-not sentences are useful. The closing sentence about the free discovery call is somewhat repetitive with the earlier 'paid execution' framing, costing a bit of tightness.

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?

Given an output schema exists and the input schema is fully annotated, the description covers the behavioral essentials an agent needs: what gets compiled, what fails, and what is returned. The only minor gap is that it does not explain the relationship to nearby tools like object_contract_check for post-hoc verification.

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 every field and the baseline is 3. The description adds marginal interpretation by enumerating the supported criterion kinds (JSON Schema, exact value, contains/not_contains, SHA-256), but this largely restates the enum already present in the schema.

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 (compile) and resource (AI agent job contract with objective acceptance criteria) into a canonical format, which is concrete and distinct from sibling tools like verify_execution or execution_proof_pack. It does not explicitly contrast with the closest siblings, but the resource is specific enough that an agent can tell what it produces.

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 gives clear context: supply goal, deliverables and at least one machine-checkable criterion, and pair the result with execution_proof_pack after delivery. It also states what it does not do (claim work, execute, move funds) and that paid execution rejects ambiguous/unsupported fields. It stops short of naming alternative tools for adjacent use cases, so not a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Agent Revenue Network 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.

Resources

Need Help?