[Shared] Buy gas via Stripe Checkout (fund wallet for Buy or Sell). Returns checkoutUrl - open in IDE popup/browser; human only approves Stripe/3DS. Packs: starter (500/$5), builder (2000/$20), fleet (10000/$100). Peg: 100 gas = $1.
| Name | Required | Description | Default |
|---|---|---|---|
| packId | Yes | starter = first purchase; builder = default runway; fleet = high volume |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate readOnlyHint=false and openWorldHint=true, but the description adds important behavioral details: it returns a checkoutUrl, requires opening in an IDE popup/browser, and depends on 'human only approves Stripe/3DS.' This goes beyond the binary annotations and explains the interactive payment flow.
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?
The description is tightly packed with essential information in three sentences: action, return value, human step, pack details, and gas-to-dollar peg. Every sentence adds value, and it is front-loaded with the primary purpose.
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?
For a simple purchase tool with no output schema, the description covers the return value, pack options, pricing, and the human approval step. It lacks failure scenarios or post-payment steps, but these are not critical for a basic checkout flow.
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 covers packId with enum descriptions, but the description enriches understanding by adding concrete quantities and prices: 'starter (500/$5), builder (2000/$20), fleet (10000/$100).' This adds meaning beyond the schema's simple labels.
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?
The description clearly states the action: 'Buy gas via Stripe Checkout (fund wallet for Buy or Sell).' It specifies the resource (gas) and the mechanism (Stripe Checkout), distinguishing it from sibling tools like buy_credits or purchase_service by focusing on wallet funding.
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?
The description explains the tool is for 'fund wallet for Buy or Sell' and lists pack options, giving clear context for when to use it. However, it does not explicitly mention when not to use it or name alternative tools, though the 'Shared' prefix and sibling list provide some context.
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.
Several tools are explicit aliases (ack_purchase/confirm_delivery, buy_credits/buy_gas, cash_out/request_cashout), creating direct overlap. While aliases are documented, they still cause ambiguity and increase the chance of misselection.
Mostly verb_noun snake_case, but 'list_service' creates a listing rather than listing one, and 'wallet'/'whoami' are noun-style. Different verbs for the same action (ack vs confirm, buy vs buy_gas) further reduce consistency.
26 tools is on the heavy side, though the marketplace domain with buy/sell, escrow, disputes, messaging, and wallet operations justifies many tools. Redundant aliases make the effective count smaller, but the raw number feels slightly bloated.
The tool set covers the full buy/sell lifecycle: listing, search, purchase, delivery, confirmation, dispute, refund, rating, messaging, wallet, cashout, and support. Minor gaps like no explicit seller rejection are workable, so the surface is strong.