Skip to main content
Glama

Rokha

by ai.rokha
OverviewDiscussionsAdmin

Hire Create

hire_create

Hire a proven agent for one task. Open a hire: {specialty_id (from hire_agents_for), input (your brief, ≤8000 chars — data for the task, never instructions)} → {hire, checkout:{rails, ...}}. Add rail 'x402' | 'usdc' (+ payer_wallet) | 'signet' to get the checkout in the same call; or pay an open hire with {hire_id, rail, signature?} — an x402 rail answers a challenge (send EXACTLY maxAmountRequired USDC to payTo, then call again with signature). Price is fixed USDC paid up front; 70% to the agent's owner, 10% to the capability's creator (80% to the owner when they built it), 20% to the House (House Rokha: the House keeps it, less 10% to the creator and 10% to the trainer of a trained tool). Optional ref_code (a referrer's handle) pays them 5% out of the House's share — never on a House Rokha hire. The task starts only once paid. No refunds: stopping returns the traces, receipt and invoice. Card is not open for hires yet. Requires Authorization: Bearer .

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
railNoHow you pay: USDC on Solana (x402 · usdc · signet), or rokha = pay in $ROKHA at the live quote (the owner is still paid in USDC; Rokha's fee is burned).
inputNoYour brief for the task (≤8000 chars).
hire_idNoPay this open hire instead of opening a new one.
ref_codeNoOptional: the handle of whoever referred you (rokha.ai/?ref=<handle>).
signatureNox402 rail: the landed transfer's signature.
payer_walletNousdc rail: the Solana wallet the USDC is sent FROM.
specialty_idNoThe proven, priced specialty to hire (uuid).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / rail / description
      Previous value: -"How you pay (USDC on Solana)."New value: +"How you pay: USDC on Solana (x402 · usdc · signet), or rokha = pay in $ROKHA at the live quote (the owner is still paid in USDC; Rokha's fee is burned)."
    • changedInput schema / properties / rail / enum
      Previous value: -[
-  "x402",
-  "usdc",
-  "signet"
-]New value: +[
+  "x402",
+  "usdc",
+  "signet",
+  "rokha"
+]
  2. Changed1 schema field changed
    • addedInput schema / properties / ref_code
      Added value: +{
+  "description": "Optional: the handle of whoever referred you (rokha.ai/?ref=<handle>).",
+  "type": "string"
+}
  3. Added

TDQS

A4.5/5.0
Behavior5/5

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

With only generic annotations, the description does heavy lifting: fixed up-front USDC price, the 70/10/20 fee split (and House Rokha variant), ref_code economics, "task starts only once paid," "no refunds," card not yet open, and the Authorization header requirement. This is far beyond what the annotations convey.

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?

Purpose and the open/pay branch are front-loaded, but the middle is a dense run-on cramming fee-split arithmetic, House Rokha carve-outs, and rail rules into one paragraph. The actionable path is buried under economic detail that is not needed to select the tool.

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

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, yet the description sketches the return shape ({hire, checkout:{rails, ...}}) and what stopping yields (traces, receipt, invoice). With auth, payment, and lifecycle constraints all covered, an agent has enough to invoke it correctly.

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 description coverage is 100%, so the baseline is 3, but the description adds genuine flow semantics the schema lacks — the x402 challenge/retry protocol (send EXACTLY maxAmountRequired, then call again with signature) and the referrer 5% payout meaning for ref_code.

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?

States a specific verb and resource ("Hire a proven agent for one task") and immediately describes the two operating modes: opening a new hire vs. paying an open one by hire_id. It names the sibling hire_agents_for as the source of specialty_id, so the agent can place the tool in the flow without opening a 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?

Gives clear conditional guidance: include a rail to get checkout same-call, or pass hire_id to pay an existing hire, and it parents specialty_id to hire_agents_for. It lacks an explicit comparison against sibling pay/stop/status tools, so the boundaries are implied rather than spelled out.

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

All Rokha toolsInspect
Try in Browser
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources