Bitquery: Crypto & Blockchain Data

Search Columns

search_columns

Read-only

FIND COLUMNS by name across the trading_rt tables — which table has a column like "supply", "fee", "pool" or "trader", with its exact name and type. query is a case-insensitive substring of the column name ("_" is literal), or a LIKE pattern when it contains % (e.g. "Price_Ohlc%"); table optionally narrows the search to table names matched the same way (e.g. "by_token"). The two combine: query "price" with table "by_token" finds the price columns of the by-token tables only. Returns at most 100 rows — exactly 100 means there are more, so narrow query or table. Rows are ordered by table, then by the column's position in it. It reads the column catalog only, never table data. Then call describe_table for the full column list of one table, and execute_sql to query it. These are NOT in the trading data, so a column search for them comes back empty — use the tool instead:

token holders → _token_holders (top holders by current balance, EVM chains); no holder-count column exists anywhere
contract events / logs / topics → _find_events, or _tx_events for known transactions
contract calls / method signatures → _find_calls
an address's transfers or balances → _transfers_in / _transfers_out / _address_profile
liquidity, TVL, pool reserves → not available in this dataset; for the pools and DEXes a token trades on use token_dex_venues
a wallet's holdings and PnL → trader_positions TransactionHeader_Fee / TransactionHeader_FeePayer are the transaction's network fee (in the chain's native coin) and its payer, not a DEX or liquidity-provider fee. chain_capabilities lists which _ tools exist; chain_search_columns searches the per-chain databases (one per call). Each row: Database, Table, Column, Type.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_columns"
  }
}

Input Schema

Name	Required	Description
`query`	Yes	Column-name text to find, case-insensitive. A substring such as "supply" or "Supply_Total" ("_" is literal), or a LIKE pattern when it contains % (e.g. "Supply%", "%_Address"). No backslashes.
`table`	No	Optional table-name filter, matched like query (e.g. "trades", "by_pool", "tokens%"). Empty = every table. No backslashes.
`database`	No	Optional. Only trading_rt can be searched with this tool; empty (the default) means trading_rt, any other value is refused — use chain_search_columns for the per-chain databases.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 7, 2026

TDQS

A4.4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description still adds real behavioral context beyond that: a hard 100-row cap with the 'exactly 100 means there are more' signal, deterministic ordering (by table then column position), and that only the column catalog is read, never table data. This is useful but scoped to a simple read tool, so it sits above the annotation baseline without being exceptional.

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 core function, return limit, and ordering are front-loaded before the long NOT-in-dataset routing list. The routing list is bulky but each bullet routes the agent to a specific sibling, so it earns its place rather than being filler.

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

Completeness5/5

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

No output schema exists, but the description fully compensates by naming the return shape ('Each row: Database, Table, Column, Type') and the cap/ordering semantics. Combined with the routing guidance, an agent has everything needed to call it correctly.

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 schema already documents the substring-vs-LIKE and table-matching rules. The description earns extra credit by spelling out the query+table combination with a worked example ('price' with 'by_token' finds price columns of by-token tables only) and by clarifying the '_' literal and % pattern behavior beyond the field text.

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?

Opens with a specific verb and resource: 'FIND COLUMNS by name across the trading_rt tables', and immediately names the sibling it is not (chain_search_columns, describe_table). An agent can tell it apart from chain_search_columns and describe_table without opening either schema.

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 chains to alternatives ('Then call describe_table ... and execute_sql to query it'), and provides a full routing table for things that are NOT in this dataset (holders, events, calls, transfers, TVL), each with the correct tool to use instead. This is near-ideal when-to-use/when-not/alternatives coverage.

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

All Bitquery: Crypto & Blockchain Data tools Inspect

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.