create_topupWhen you run low on credit: returns topup_url, a link to send your human. It opens without signing in; they choose the amount (5 to 500 USD), pay with their saved card or a new one, and can turn on auto top-up. Works for 7 days. You cannot pay it yourself. Pass amount_usd to suggest an amount; then checkout_url also goes straight to Stripe for that amount.
| Name | Required | Description | Default |
|---|---|---|---|
| amount_usd | No | Suggested amount in whole US dollars (optional) |
Changes observed during successful MCP inspections.
Input schema / properties / amount_usd / descriptionAdded value: +"Suggested amount in whole US dollars (optional)"Input schema / properties / amount_usd / enumRemoved value: -[
- 10,
- 25,
- 50
-]Input schema / properties / amount_usd / examplesAdded value: +[
+ 10,
+ 25,
+ 50,
+ 100
+]Input schema / properties / amount_usd / maximumAdded value: +500Input schema / properties / amount_usd / minimumAdded value: +5Input schema / properties / amount_usd / typePrevious value: -"number"New value: +"integer"Input schema / requiredRemoved value: -[
- "amount_usd"
-]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (which only say it's non-read-only, non-idempotent, non-destructive), the description discloses substantial behavior: the link opens without sign-in, is valid for 7 days, lets the human pick the amount, supports saved or new cards and auto top-up, and cannot be paid by the agent itself. This is exactly the context annotations cannot convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loads the trigger, then layers mechanism, constraints, and the parameter note in compact sentences. Slightly dense but every clause (expiry, no sign-in, self-pay prohibition) carries useful information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description steps in to describe the returned topup_url and optional checkout_url, plus validity window and payer rules. Complete for an agent to invoke it correctly; only the sibling-alternative routing is left implicit.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3, but the description adds real meaning: amount_usd is a *suggestion* (the human still chooses), and setting it also produces a checkout_url going straight to Stripe. That clarifies intent and side effect beyond the schema's 'Suggested amount' text.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific outcome: it returns topup_url, a link to send to the user, and optionally a checkout_url. The purpose (generate a human-payable top-up link) is unambiguous, though it never explicitly contrasts itself with the sibling charge_saved_card, which an agent might otherwise consider.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Opens with an explicit trigger condition, 'When you run low on credit', and adds the routing constraint 'You cannot pay it yourself', which tells the agent to hand off to the human rather than paying directly. It stops short of naming charge_saved_card or get_balance as alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.