Skip to main content
Glama
TickerDB

TickerDB

Official

query

Read-only

Retrieve point-in-time stock, ETF, and crypto snapshots or history with fields, filters, dates, and ranges to build ranked screens and store large pulls for later analysis.

Instructions

Any cross-section or history (one ticker's full snapshot: get_summary). Give fields and filters (names from get_schema), then EITHER date (default latest) OR start+end. One date with filters, tickers, sort_by or limit: a ranked screen. One date with only fields: every asset. A range: every row in it, weekly by default past ~6 months; market_/macro_ filters keep only dates in that regime, other filters apply after the rows are fetched, so narrow with tickers, member_of or asset_class. Big pulls: store_as + fetch_all, then query_data.

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": "query"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoRange end (YYYY-MM-DD).
dateNoOne date; default latest (YYYY-MM-DD).
limitNoRows on one date (default 20, max 250); rows per page on a range.
ohlcvNoRange only: add ohlcv_open/high/low/close/volume.
startNoRange start, with end (YYYY-MM-DD).
appendNoAdd rows to an existing store_as table instead of replacing it.
fieldsNoColumns, e.g. ["market_cap_usd","momentum_rsi_zone"]. Max 30.
offsetNoOne date: skip this many ranked rows.
dry_runNoRange: returns what it would cost in credits. No data, no charge.
filtersNoUp to 10; a row must match all of them, and null matches none. E.g. [{"field":"momentum_rsi_zone","op":"in","value":["oversold"]}].
held_byNoOnly assets this fund held on the row's date: fund ticker (IVV) or SEC series id.
sort_byNoTicker field to rank by (one date).
tickersNoOnly these tickers.
store_asNoTable name: store rows in SQLite, return only a summary. Read with query_data.
fetch_allNoFollow every page into store_as in this one call.
member_ofNoOnly members of this index on the row's date, e.g. sp500. Ids: get_indexes.
timeframeNoDefault: weekly for ranges over ~6 months, else daily.
adjustmentNoWith ohlcv: split (default), split_dividend (total return) or raw (as traded).
page_tokenNoRange: a token from page_tokens or next_page_token (same params).
asset_classNoOnly this asset class.
sort_directionNoDefault desc.

Output Schema

NameRequiredDescriptionDefault
dataNoThe tool's result.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.1

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful behavior beyond them: filter evaluation order (market_/macro_ filter dates before fetch, other filters apply after rows are fetched), weekly resampling default past ~6 months, credit-costing dry_run, and store_as replacing vs append. It does not describe return shape, but an output schema exists, so this is solid if not rich.

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?

Extremely compact for a 21-parameter tool, with scoping and mode selection front-loaded and no filler sentences. The telegraphic fragments ('Any cross-section or history', 'Big pulls: store_as + fetch_all') are efficient but occasionally force re-reading, which is the main cost.

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?

Covers mode selection, filter ordering, pagination-by-store workflow and cost checks, which is most of what an agent needs for a 21-parameter query. The gaps are interpretive rather than structural: the terse phrasing leaves mode boundaries somewhat implicit, and an agent could mis-assemble date plus start/end. With an output schema present, return values need not be explained.

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, and the description earns above that by adding combination semantics the schema lacks: date defaults to latest, date must pair with either date or start+end, and the mode changes what the query means (ranked screen vs full asset set vs full range). It also warns that narrowness should come from tickers, member_of or asset_class when filters apply post-fetch. Individual parameter formats remain the schema's job.

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?

States a specific verb and resource: querying cross-section or history of asset data, with the modes (one date, range) named. It explicitly hands off one-ticker snapshots to get_summary, so an agent can separate the two tools without opening schemas. The opening parenthetical is compressed and slightly cryptic, which keeps it short of perfect.

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?

Gives concrete routing rules: names from get_schema, EITHER date OR start+end, one date plus filters/tickers/sort_by/limit for a ranked screen, one date with only fields for all assets, a range for every row. It also names alternatives (get_summary, get_schema, query_data) for adjacent jobs. It falls short of 5 because it does not explicitly say when not to use it beyond the get_summary carving.

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