card_getRetrieve a prepaid card you own: full card number, CVV, expiry, live balance. Owner-verified (0.01 USDC ownership proof; the paying wallet must be the card's buyer).
| Name | Required | Description | Default |
|---|---|---|---|
| card_id | Yes | card_id returned by card_buy | |
| payment | No | base64 x402 payment payload (X-PAYMENT); omit on first call to receive payment instructions |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It thoroughly discloses the ownership verification requirement (0.01 USDC proof, paying wallet must be buyer) and the two-step payment flow for accessing sensitive card data. This goes beyond a simple 'get' and informs the agent of important prerequisites and consequences.
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 well-structured sentences. The first sentence states the purpose and return data, and the second adds the critical ownership proof requirement. No filler or redundancy; every word earns its place.
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?
Although there is no output schema, the description explicitly lists the returned fields (card number, CVV, expiry, live balance), covers the payment flow (first call vs. subsequent), and states the ownership verification constraint. For a sensitive financial data retrieval tool, this is comprehensive given the available schema and annotations.
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?
The schema already documents both parameters with 100% coverage, providing a baseline of 3. The description adds meaningful context about the payment parameter by explaining the ownership proof and its relationship to the card buyer, enriching the schema's terse description. This additional context justifies a 4.
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 begins with a specific verb+resource: 'Retrieve a prepaid card you own' followed by the exact data fields returned (full card number, CVV, expiry, live balance). This clearly distinguishes it from siblings like card_list (which likely lists cards) and card_status (which likely shows status), making the purpose unambiguous.
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 provides clear context for when to use the tool: it is for retrieving a card you own, and it explains the ownership proof requirement. It also gives specific usage guidance for the payment parameter ('omit on first call to receive payment instructions'). However, it does not explicitly mention alternative tools or when not to use this one, so it's strong but not fully explicit.
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.
Each tool targets a distinct resource and action, clearly separated by domain prefixes (card_, email_, phone_, tiktok_). The only potential overlap is phone_read_messages vs wait_for_otp, but wait_for_otp is specifically for OTP extraction and is described as a replacement for hand-rolled polling, making the boundary clear. Status pollers are also domain-specific (card_status, tiktok_connect_status, tiktok_operation_status) and not ambiguous.
All tool names follow a consistent snake_case convention with domain-first prefixes (e.g., card_buy, email_send, tiktok_post, phone_temp_number). Even less common names like wait_for_otp and i402_plan are descriptive and stylistically consistent. There are no mixed conventions or vague verbs.
33 tools is above the typical 3-15 range, but the server covers a broad multi-domain purpose (cards, compute, domains, email, phone, TikTok, Twitter, orchestration). Each domain has a focused and coherent set, so the count feels justified rather than bloated. It is slightly high, but not excessively so.
Coverage is solid for email, phone, and TikTok, with full lifecycle operations (create, read, extend, delete/cancel where applicable). However, there are notable gaps: compute has only deploy (no list/stop/delete), domains have only check/register (no list/delete), and Twitter has only post (no read/manage). These gaps could force agents to work around missing resource management.