Skip to main content
Glama

TILLA - market data on one clock

Bars in a time range

tilla_window
Read-onlyIdempotent

A window of bars. Name exactly what you want, one of: series = comma-separated names (at most 200) from tilla_inventory, or a pattern like 'btc_*' / '*_close'; or markets + fields ('btc,eth' + 'close,volume' -> btc_close, btc_volume, eth_close, eth_volume). layer = raw | derived | node | deep; lane = 1min, 5min, hour, daily, ... start/end = 'YYYY-MM-DD[ HH:MM[:SS]]' UTC inclusive, or period = 30d 2m 6m 1y all; no start = the newest bars. limit <= 50000. When more is true, call again with start = next_start. Needs your API key (hosted: the X-API-Key header; local: TILLA_API_KEY).

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": "tilla_window"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNo
laneNo1min
layerNoraw
limitNo
startNo
fieldsNo
periodNo
seriesNo
marketsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds genuinely non-derivable behavior: it requires an API key (X-API-Key header hosted, TILLA_API_KEY local), discloses the pagination contract via `more`/`next_start`, the 50000 limit ceiling, UTC and inclusive boundary semantics, and that omitting start returns the newest bars.

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?

It is dense and mostly front-loaded: the selection modes come first, then layer/lane, then time range, then limit and pagination, then auth. Almost every clause earns its place, though the run-on backtick-heavy sentences and mid-sentence line breaks make it harder to scan than it needs to be.

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 9-parameter, no-output-schema read tool this is close to complete: selection modes, time semantics, paging and auth are all covered. The main gap is that the `layer` values (raw vs derived vs node vs deep) are enumerated but never explained, and the shape of a returned bar is left implicit.

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

Parameters5/5

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

Schema coverage is 0% and there are 9 parameters, so the description carries the full burden and does so for every one: `series` (comma-separated, max 200, wildcards like 'btc_*'), `markets`+`fields` expansion (btc,eth + close,volume -> btc_close, ...), `layer` (raw|derived|node|deep), `lane` (1min, 5min, hour, daily, ...), `start`/`end` ('YYYY-MM-DD[ HH:MM[:SS]]' UTC inclusive), `period` (30d 2m 6m 1y all) and `limit` (<= 50000). This adds value far beyond the bare schema titles.

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 (bars) and its scope (a window over a time range, per lane/layer), so an agent knows this is a bulk time-series retrieval. It does not, however, contrast itself with near-neighbours like tilla_latest, tilla_sample or tilla_tick, so the differentiation is left implicit.

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?

It gives strong in-tool usage rules: selection must be exactly one of `series` or `markets`+`fields`, defaults apply when no start is given, and when `more` is true you re-call with start = `next_start`. What is missing is when to prefer this over sibling tools (tilla_latest for the newest bar, tilla_tick for a single tick), which is the core of this dimension.

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.