Skip to main content
Glama

CARV hub: $CARV market, contracts, official links, @carv_official posts

get_carv
Read-only

The $CARV developer API as one tool (v5.691): what=market (price, 24h change, volume, high, low, market cap, supply, rank, ATH), history (daily candles, days=2 to 1000), supply, contracts (the OFT address on Ethereum, Base, Arbitrum One, BSC, Linea, the Solana mint, veCARV staking, CARV ID), links (carv.io, docs, stake.carv.io, explorer.carv.io/verifiers, SVM explorer, bridge, RPC, GitHub, X, Telegram, Discord, Medium) x (@carv_official posts with their age; says when they are picked by hand), brief (v5.887: today in one call: one facts object, the strings the hub prints, the plain read, the checked AI note, volume by venue over five venues, the KRW market with the Upbit premium) or drivers (v5.887: what moves CARV: 30 and 90 day correlation with BTC, the AI tokens FET, TAO, VIRTUAL, NVDA, Nasdaq, SOXX, KOSPI, KOSDAQ, with a plain word Strong, Medium or Weak). market volume is the sum of Binance perp, Bybit perp and spot, Upbit and Bithumb. Hub: owlchart.com/carv-hub.html, docs: owlchart.com/carv-api.html.

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": "get_carv"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNohistory: how many daily candles, default 90; drivers: 30 or 90
whatNowhich CARV data set, default market; nvidia (v5.898) is CARV against Nvidia: link, beta, big Nvidia days, results days and the nights

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / what / description
      Previous value: -"which CARV data set, default market"New value: +"which CARV data set, default market; nvidia (v5.898) is CARV against Nvidia: link, beta, big Nvidia days, results days and the nights"
    • changedInput schema / properties / what / enum
      Previous value: -[
      -  "market",
      -  "history",
      -  "supply",
      -  "contracts",
      -  "links",
      -  "x",
      -  "brief",
      -  "drivers"
      -]New value: +[
      +  "market",
      +  "history",
      +  "supply",
      +  "contracts",
      +  "links",
      +  "x",
      +  "brief",
      +  "drivers",
      +  "nvidia"
      +]
  2. Changed2 schema fields changed
    • changedInput schema / properties / days / description
      Previous value: -"history only: how many daily candles, default 90"New value: +"history: how many daily candles, default 90; drivers: 30 or 90"
    • changedInput schema / properties / what / enum
      Previous value: -[
      -  "market",
      -  "history",
      -  "supply",
      -  "contracts",
      -  "links",
      -  "x"
      -]New value: +[
      +  "market",
      +  "history",
      +  "supply",
      +  "contracts",
      +  "links",
      +  "x",
      +  "brief",
      +  "drivers"
      +]
  3. Added

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, but the description adds real behavioral context: it discloses the volume aggregation methodology (Binance perp + Bybit perp + spot, Upbit, Bithumb) and that X posts are 'picked by hand' and carry their age. It omits freshness/caching behavior and rate limits, and the version stamps add no behavioral value.

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

Conciseness2/5

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

The opening 'The $CARV developer API as one tool (v5.691)' is vague and the release tags v5.691/v5.887/v5.898 are noise that does not help an agent choose or call the tool. Nine modes are crammed into a single sprawling sentence with nested parentheses, making it hard to scan even though the raw information is dense.

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?

For a nine-mode hub with no output schema, the description does the necessary work of sketching each mode's payload and the venue methodology behind volume. The main omission is the v5.898 'nvidia' mode, which exists only in the schema and is not surfaced in the prose.

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?

Schema coverage is 100%, so the baseline is 3; the description does add meaning by stating defaults (market, 90 days) and that drivers accepts only 30 or 90 while history spans 2–1000. It leaves the 'nvidia' enum value unexplained, relying on the schema for that mode.

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 names the resource ($CARV) and enumerates exactly what each mode returns (market, history, supply, contracts, links, x, brief, drivers), which is far more specific than the title alone. It stops short of differentiating itself from siblings such as get_nvidia and get_token_hub, despite carrying an overlapping 'nvidia' mode.

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 only implied through mode glosses like 'brief (today in one call)' and 'drivers (what moves CARV)', which hint at when each mode is appropriate. There is no explicit when-to-use/when-not guidance and no routing advice versus the sibling get_nvidia despite the overlapping Nvidia mode.

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.

Resources