Skip to main content
Glama

Extend a rental (spends balance)

extend_rental
DestructiveIdempotent

SPENDS MONEY from the prepaid ipvolt balance of the credential's account. Extend one of the account's active rentals by 1 or 30 days. Two steps: (1) call without confirm: this only looks up the current price and answers the exact charge and a requestId; nothing is charged. (2) Only after the user approved that charge, call again with confirm: true and that requestId. If the price rose meanwhile the API refuses instead of charging more, and repeating a confirmed requestId returns the same order without charging again. Needs a read-write API key, an agent token that may buy, or the order's invoice ID.

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": {
      "rentalId": "<rentalId>",
      "days": "<days>"
    },
    "name": "extend_rental"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysYesExtend by 1 or 30 days.
confirmNoLeave out to preview the charge. Set true, with the preview requestId, only after the user approved that charge.
rentalIdYesRental id from list_rentals.
requestIdNoThe requestId the preview returned, copied exactly. Use it only with confirm: true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, and openWorldHint=true, so the safety profile is partly covered; the description nonetheless adds substantive context beyond them, including that a confirmed requestId is replayed idempotently instead of double-charging, that a price increase results in refusal rather than a larger charge, and which credential types are accepted. Only the return payload shape is left implicit, which is minor.

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 money-spending warning in caps, then presents the two steps as numbered clauses so the agent cannot misread the ordering. Every sentence carries a distinct constraint (charge preview, user approval, price-rise refusal, idempotent replay, auth) with no 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?

For a destructive, balance-spending mutation with four parameters and no output schema, the description covers the confirmation workflow, retry safety, price-change behavior, and required credential types. Nothing an agent needs in order to invoke it safely is missing.

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 earns above that by explaining the coupling between confirm and requestId as a workflow contract (preview returns the requestId, confirm consumes it, and a stale price is refused). The days parameter meaning beyond its enum is not elaborated, which keeps it from a 5.

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?

Opens with a specific verb and consequence ("SPENDS MONEY from the prepaid ipvolt balance") plus the exact resource and scope ("Extend one of the account's active rentals by 1 or 30 days"). An agent can distinguish this from read-only siblings like get_rental or list_rentals immediately, and the title reinforces the destructive nature.

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 an explicit two-step protocol: call without confirm to preview the charge, then call again with confirm:true only after the user approved that charge. The when-not condition ("only after the user approved") is stated, and the failure semantics (price rose → refusal) tell the agent what to do next. Sibling alternatives for creating new rentals aren't named, but the procedural guidance is unambiguous.

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