Skip to main content
Glama

AgentData — crypto market data with a checkable record

by io.github.speteai
OverviewDiscussionsAdmin

get_changes_since_last_call

Only what changed for a signal since THIS wallet last paid for it ($0.001 USDC — cheaper than any full payload). Replaces repeated polling: the server keeps the cursor, keyed to your wallet, so you never re-download or re-diff data you already have. Requires signal=. First call returns the last 24h.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
signalYessentiment, funding-rates, liquidation-levels, volatility, correlation, positioning, supply, stablecoin-health, macro-onchain, defi-yields, dex-vs-cex, arbitrage-opportunities, funding-predictions
paymentNoOptional. Base64 x402 payment payload you signed yourself (ERC-3009 TransferWithAuthorization, USDC on Base). Call without it once to receive the payment requirements, sign those, then call again with this argument. This server forwards the payload and never holds a key.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / payment
      Added value: +{
+  "description": "Optional. Base64 x402 payment payload you signed yourself (ERC-3009 TransferWithAuthorization, USDC on Base). Call without it once to receive the payment requirements, sign those, then call again with this argument. This server forwards the payload and never holds a key.",
+  "type": "string"
+}
  2. Added

TDQS

A4.2/5.0
Behavior4/5

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

Even with no annotations, the description carries its weight: it discloses server-side cursor state keyed to the wallet, that it prevents re-downloading/re-diffing, and that the first call returns the last 24h. It leaves some behavior around payment requirements implicit, but the schema's payment parameter description covers that flow.

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 description is compact and front-loaded: the core value and differential are in the first sentence. The phrase 'Requires signal=' is a bit clipped, but no sentence is wasted and the description also lands key pricing and behavior facts.

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?

The tool has no annotations and no output schema, and the description does not describe the response shape or list expected return fields. This leaves an agent unsure what 'changes' looks like. The how and why of polling are well covered, but given no output schema, a little more on the returned data structure would be needed for full completeness.

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 baseline is 3. The description adds meaningful context by revealing the cost of the payment payload, wallet-keyed state, and the 24h initial time window, which helps an agent understand the payment parameter's purpose and how the signal cursor behaves.

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 states a specific verb+resource: return only what changed for a given signal since this wallet last paid for it. It clearly differentiates from the many get_* sibling snapshot tools by calling itself a delta endpoint that is 'cheaper than any full payload' and a replacement for repeated polling.

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

Usage Guidelines4/5

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

The description explicitly explains when to use the tool: when you need incremental changes rather than a full payload, and as a replacement for repeated polling. It does not explicitly name sibling alternatives or state 'use get_<signal> for full data', but the contrast is clear enough.

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

All AgentData — crypto market data with a checkable record toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources