Skip to main content
Glama

buy_credits

Purchase credits for Varrd's MCP server using USDC on Base network. Get a deposit address, send USDC, then confirm payment to receive credits for market analysis tools.

Instructions

Buy credits with USDC on Base. Two modes:

  1. Call without payment_intent_id to get a Stripe deposit address.

  2. Send USDC to that address, then call again with the payment_intent_id to confirm and receive credits. Default $5. Free — no credits consumed to call this.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
amount_centsNoAmount in cents (default 500 = $5.00). Minimum $5.
payment_intent_idNoStripe PaymentIntent ID from a previous buy_credits call. Pass this after sending USDC to confirm payment and receive credits.
Behavior4/5

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

Supplements annotations significantly by explaining the external dependencies (Stripe for deposit addresses, Base blockchain for USDC), the stateful two-step commitment pattern, and the specific cost model (free to call). Does not contradict annotations (readOnlyHint=false aligns with 'Buy' mutation). Could mention error states or timeout behavior for full marks.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Information is densely packed and front-loaded. The numbered list efficiently communicates the sequential workflow. The final sentence about cost stands alone for visibility. Slightly informal structure ('Two modes:') but zero wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Appropriately complete for a two-parameter tool with complex external interaction. Describes both initiation and completion return values (deposit address vs credits received) despite no output schema. Missing only edge case handling (e.g., expiration of payment intents).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the schema already clearly documents both parameters (amount_cents semantics and payment_intent_id purpose). The description adds workflow context for when to use payment_intent_id, meeting the baseline expectation when structured data is complete.

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?

The description clearly states the specific action ('Buy credits'), the payment method ('USDC on Base'), and the platform. It distinctly differentiates from siblings like 'check_balance' or 'research' by focusing on a payment transaction workflow.

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?

Explicitly documents the two-step workflow: first call to get deposit address, second call with payment_intent_id to confirm. States the default amount ($5) and critical cost information ('Free — no credits consumed to call this'), which helps users understand they can safely initiate step 1 without charge.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/augiemazza/varrd'

If you have feedback or need assistance with the MCP directory API, please join our Discord server