Rooms Agent Pay (sandbox preview)

create_room

Open a Rooms Agent Pay room for a goal with a budget (USD) and an approval line. Returns one ready-to-pay link the human opens to fund it with PayPal or a card (SANDBOX: no real money). Unspent budget stays in the room as credit for the next hire.

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>",
      "cap": "<cap>"
    },
    "name": "create_room"
  }
}

Input Schema

Name	Required	Description
`cap`	Yes	Budget in USD to put in the room (minimum applies, e.g. 25)
`goal`	Yes	What the room should get done
`email`	No	Funder email (optional; first room's fee is waived for a new email)
`approval_line`	No	Hires above this USD amount wait for the owner's OK

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

A3.8/5.0

Behavior4/5

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

With no annotations, the description carries real behavioral weight: it discloses that the return is a single ready-to-pay link, that a human must open it to fund via PayPal or card, that this is SANDBOX with no real money, and that unspent budget persists as credit. It does not cover repeat-call behavior (does a second call open a second room?) or link expiry, which are the remaining behavioral gaps.

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?

Three front-loaded sentences with no filler: purpose, return/funding mechanics, then the credit-carryover detail. Every sentence adds information an agent would otherwise have to guess.

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 no output schema and no annotations, the description does explain the return value (one funding link) and the sandbox safety profile, which is the critical missing piece elsewhere. It stops short of describing room lifecycle (expiry, what close_room later does to the credit), so it is strong but not fully complete for a multi-step money-flow tool.

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 coverage is 100%, so the baseline is 3; the schema already defines cap, goal, approval_line, and email. The description adds only the relationship between cap and leftover credit, and says nothing about the email parameter's fee-waiver benefit, which the schema already covers anyway.

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 and resource — 'Open a Rooms Agent Pay room' — plus the three things it is parameterized by (goal, budget in USD, approval line). It does not explicitly name a sibling or contrast itself against close_room/room_status/hire_specialist, so differentiation is inferred rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the funding flow and by 'credit for the next hire', which signals this is the setup step preceding hiring, but the description never says when to use this versus the other room tools or what conditions make it inappropriate (e.g. already having an open room).

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

All Rooms Agent Pay (sandbox preview) 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?