Skip to main content
Glama

MoneyTools payment-safety suite

Ask your human to approve a payment

approval_request

Create a human approval request (Approval Relay). Show approveUrl / approve_url to your human, then poll approval_status. Served by Approval Relay at relay.moneytools.dev (0.005 USDC, 3 free/day; signed Ed25519 receipt). Old field names (title, approveUrl, id, agentToken, proof) are still accepted and returned as aliases. approve.moneytools.dev stays available for existing HTTP/MCP callers.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "approval_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostNoOptional context folded into action_summary
riskNoRisk level shown to the approver (default med)
payToNoOptional context folded into action_summary
titleNoAlias of action_summary (legacy approval_request field)
notifyNoLegacy; notify.webhook is used as callback_url if set
detailsNoOptional extra context folded into action_summary
networkNo
amountUsdNoOptional context folded into action_summary
requesterNoOptional label shown to the approver
ttlMinutesNoLegacy alias of expires_in_s (minutes, 5-1440)
callback_urlNoOptional https callback that receives the signed receipt
expires_in_sNoSeconds until expiry (default 3600)
action_summaryNoPlain-language description of the action (preferred)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only supply readOnlyHint=false and openWorldHint=true, so the description carries the burden and does well: it discloses pricing (0.005 USDC, 3 free/day), a signed Ed25519 receipt, and callback delivery to callback_url. It omits auth requirements (the legacy agentToken is mentioned only as an alias) and what happens if the request expires unapproved.

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?

Front-loaded with the action and the immediate next step, and most sentences carry unique information (cost, receipt, aliases). The closing note about approve.moneytools.dev staying available for existing HTTP/MCP callers is migration trivia that an agent doesn't need in order to call the tool.

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 13-parameter, zero-required, open-world mutation with no output schema, the description covers cost, receipt signing, callback, and legacy compatibility well. It stops short of describing the returned handle/id or the polling cadence, which an agent must infer.

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 92%, so the schema already documents nearly every field; the description's main addition is that legacy names (title, approveUrl, id, agentToken, proof) are still accepted as aliases, which is genuinely beyond the schema. It adds no format or constraint detail for the primary fields like action_summary or expires_in_s beyond what the schema states.

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 ('Create a human approval request') and names the downstream artifact (approveUrl) plus the sibling to poll (approval_status). An agent can distinguish this create step from approval_status/approval_consume 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?

Gives an explicit two-step workflow: create the request, show approveUrl to the human, then poll approval_status. It does not state when to prefer this over approval_cancel/approval_consume or what to do on expiry, so it falls short of full when/when-not guidance.

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.

Resources