Skip to main content
Glama
Sign In

spendctl

by dev.spendctl
OverviewDiscussionsAdmin

Wait for a held sandbox payment's decision

await_approval
Read-only

Waits for the decision on a payment that sandbox_pay reported as held, without paying again: long-polls the sandbox sidecar for up to timeoutSeconds (default 10, at most 20) and returns pending, approved, denied, expired or withdrawn, with the ledger entry and the decision deadline. This is what an agent does in the real product while a human decides; in the sandbox the model is also the approver (approve), so call approve from another turn or first. After approved, repeat sandbox_pay with approvalId to complete the payment. Read-only; never pays and never decides.

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": {
      "sandbox_id": "<sandbox_id>",
      "approvalId": "<approvalId>"
    },
    "name": "await_approval"
  }
}

Input Schema

NameRequiredDescriptionDefault
approvalIdYesThe approval id returned by sandbox_pay in its "waiting for approval" result (Approval id: ...)
sandbox_idYesThe sandbox_id returned by sandbox_create (32 hex characters)
timeoutSecondsNoHow long to wait for a decision before answering pending (1 to 20, default 10)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

Adds substantial behavioral detail beyond the readOnlyHint: it long-polls the sidecar for up to timeoutSeconds, returns pending/approved/denied/expired/withdrawn, and includes the ledger entry and decision deadline. It reinforces that the tool never pays and never decides, which is important for an awaiting-decision operation.

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?

Front-loads the core purpose in the first clause, then adds timeout/return behavior, usage guidance, follow-up, and safety in a compact sequence. Every sentence contributes useful context without redundant filler.

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?

Complete for this tool: it explains the wait behavior, possible decisions, timeout semantics, approval workflow, and post-approval completion step. With no output schema, the description appropriately describes return statuses and accompanying data.

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 sandbox_id, approvalId, and timeoutSeconds fully. The description only repeats the timeout default and maximum, adding little beyond the schema baseline.

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: waits for the decision on a held sandbox payment. It explicitly distinguishes itself from sandbox_pay by saying it does not pay again, and ties into approve as the mechanism that produces the decision.

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

Usage Guidelines5/5

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

Gives clear when-to-use context: call this after sandbox_pay reports a held payment, do not pay again, and use approve from another turn because the model is also the approver in sandbox. It also gives the follow-up action: repeat sandbox_pay with approvalId after approval.

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

All spendctl toolsInspect
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