Skip to main content
Glama

ARL Protocol

arl_prepare_job

Step 1 of opening a task as a verified job: validates the task against its policy and returns the unsigned createJob transaction for the user's own wallet (the client) to sign and send on Base Mainnet. Read the jobId from the JobCreated event of its receipt, then call arl_prepare_funding.

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": {
      "task": "<task>",
      "taskUri": "<taskUri>",
      "client": "<client>",
      "provider": "<provider>",
      "committee": "<committee>"
    },
    "name": "arl_prepare_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskYesAn arl-task/1 document (spec/arl-task/v0.1.0 in github.com/armanalabsai/arlcoin.io)
clientYesThe user's wallet: it signs and pays
policyNoThe arl-policy/1 document the task names; omit for a built-in policy
taskUriYeshttps or ipfs URI where validators fetch the task document
providerYesThe agent or service doing the work
committeeYesStaked validators, as many as the task's committee_size

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations supplied, the description does the heavy lifting well: it states the tool only validates and returns an unsigned transaction, that the user's own wallet is the signer and payer, and that the target chain is Base Mainnet — all material for a transaction-producing tool. Gaps remain around failure behavior (validation rejection), whether any state changes, and idempotency of repeated prepares.

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

Conciseness5/5

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

Two dense sentences, front-loaded with the identity and step position, then the post-call protocol (read jobId from the JobCreated event, then call arl_prepare_funding). No filler or redundant restatement of the tool name.

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?

For a six-parameter, nested-object, no-output-schema tool, the description covers identity, chain, signer, return value (unsigned createJob transaction) and the follow-up procedure. The main shortfall is that it does not say what the tool returns or does when policy validation fails, which matters for an agent driving a multi-step commit flow.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description goes slightly beyond the schema by tying the `client` parameter to the signing/paying role and framing `policy` as the object the task is validated against, which clarifies how the required fields relate to each other in the flow rather than merely restating them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

A specific verb ('validates ... and returns the unsigned createJob transaction') plus an explicit scope: it prepares, but does not send, a transaction on Base Mainnet. It also maps the step in a sequence ('Step 1') and names the successor tool, so an agent can place it relative to arl_prepare_funding without opening any schema.

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 workflow position is unambiguous — call this to open a task as a verified job, then hand the returned unsigned transaction to the client to sign and send, then call arl_prepare_funding. What is missing is exclusions: there is no statement about when not to use it (e.g. before the task passes arl_check_task) or what to do if policy validation fails.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.