Add credits when your $5 free balance runs out. Pay via USDC crypto (provide tx_hash) or get a Stripe checkout link for your human operator to complete.
| Name | Required | Description | Default |
|---|---|---|---|
| amount | Yes | Amount in USD to add | |
| method | Yes | Payment method | |
| api_key | Yes | Your API key | |
| tx_hash | No | USDC transaction hash (for crypto payments) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description works to disclose behavior. It clearly outlines the two payment flows and notes that Stripe requires human involvement. However, it doesn't state what happens after the payment (e.g., immediate credit, confirmation response) or any post-conditions.
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 two sentences, front-loaded with the core purpose, and contains no redundant information. Every clause contributes meaningful guidance.
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?
The tool handles payments, and the description covers the trigger, the two payment methods, and the human-in-the-loop Stripe step. It lacks details on response behavior (no output schema), but for a payment top-up tool, the operational context is sufficiently clear.
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 the baseline is 3. The description adds value by clarifying the dependency between method and tx_hash: USDC requires tx_hash, while Stripe yields a checkout link. This helps the agent correctly assemble parameters beyond the schema's field-level descriptions.
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 ('Add credits') and the specific trigger ('when your $5 free balance runs out'). It distinguishes itself from siblings like check_balance (which verifies balance) and purchase_data (which buys data) by focusing on the credit top-up action.
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 gives explicit timing ('when your $5 free balance runs out') and details the two payment methods: USDC crypto (with tx_hash) and Stripe (which generates a checkout link for a human). It doesn't explicitly mention alternatives, but the context is sufficient to know when to use this tool.
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.
Most tools target distinct actions (browse, query, purchase, top-up), but get_zk_provenance and verify_footprint both promise cryptographic verification for datasets/records and could easily be confused. fetch_dataset vs get_stats also has mild overlap, but the descriptions clarify querying records vs. aggregate statistics.
All tools follow a consistent snake_case verb_noun pattern: check_balance, fetch_dataset, list_products, purchase_data, register_agent, etc. The verbs are action-oriented and the nouns correspond to the resource being handled.
Ten tools cover registration, billing, product browsing, data querying, stats, and verification without feeling bloated. The count is typical for a marketplace/API server and each tool serves a concrete step in the user journey.
The core lifecycle is complete: register, view credits, browse products, buy, query, verify, and top up. Minor gaps exist around post-purchase management, such as listing owned subscriptions/entitlements or managing/rotating the API key, but agents can complete the main workflows without dead ends.