Skip to main content
Glama

APEX 373 x402 & Card API-Key Agent Tools

Referral

referral

The referral programme, open to agents on the same terms as people. Pass a wallet to see that wallet's code, referral count and earnings; pass wallet AND code to claim a code. The reward is an ongoing SHARE, not a signup bonus: you earn a percentage of every APEX claim made by anyone you referred, every time they claim, for as long as they keep claiming. It is paid in APEX from the faucet's daily budget and is capped, so it can never exceed a fixed slice of what your referrals themselves receive.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "referral"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeNoOptional. 3-15 chars [A-Z0-9_] to claim as your referral code.
walletNoYour X1 wallet address (32-44 chars, Solana-style — not 0x).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioural burden. It explains the economic behaviour of the reward well (an ongoing share of every APEX claim by referrals, paid from the faucet's daily budget and capped), which is genuinely useful context. But it says nothing about the tool's own behaviour contract: whether claiming is a mutation with side effects, whether it costs anything, whether codes are unique/permanent, what happens if a code is already taken, or what the claim response contains.

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?

The mode dispatch is front-loaded in the second sentence, and the reward explanation follows as supporting context. It is not bloated, though the reward clause is repetitively emphatic ('every APEX claim ... every time they claim, for as long as they keep claiming'), and the opening framing sentence earns little space.

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

Completeness3/5

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

For a two-parameter tool with no output schema, the description should fully cover both modes. The read mode's return values are listed, but the claim mode's outcome is never described, and with zero annotations there is no safety profile for what is likely a write operation. Adequate, but with a clear gap on the mutating path.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description goes beyond the schema by explaining what the optionality of `code` actually means: wallet alone selects lookup mode, wallet plus code selects claim mode. The schema only labels `code` as 'Optional', so this is a real semantic addition rather than a restatement. It does not add format or validation detail beyond the schema's own constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the two operating modes precisely: pass a wallet to read that wallet's code, referral count and earnings, or pass wallet AND code to claim a code. That is a concrete verb+resource pair for each path. It falls short of a 5 because the opening sentence ('The referral programme, open to agents on the same terms as people') is positioning rather than purpose, and no sibling tool is named or contrasted.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied through the argument pattern: one argument for a lookup, two for a claim, which effectively tells the agent which mode it is entering. However, there is no explicit when-to-use guidance, no prerequisites (e.g., do you need a funded wallet or to have onboarded first?), and no mention of any alternative tool for related needs. The agent must infer the boundary between the read and write behaviours.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.