Skip to main content
Glama
TickerDB

TickerDB

Official

query_data

Run read-only SQL queries against in-memory TickerDB market data tables to filter and analyze saved results, returning up to 200 rows or exporting full results to CSV.

Instructions

Read-only SQL (SQLite) over tables saved with store_as: SELECT or WITH, plus SHOW TABLES and DESCRIBE . Returns at most 200 rows; output_path writes the full result to a CSV file for bulk work. Nested fields are flattened with _ (trend.direction -> trend_direction); booleans are 1/0. Tables live in memory for this server process.

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": {
      "sql": "<sql>"
    },
    "name": "query_data"
  }
}

Input Schema

NameRequiredDescriptionDefault
sqlYesOne statement.
formatNocsv: rows as CSV text. Default json.
max_rowsNoDefault 200.
output_pathNoCSV file path for the full result (every row).

Output Schema

NameRequiredDescriptionDefault
dataNoThe tool's result.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.1

TDQS

A3.9/5.0
Behavior3/5

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

Adds real behavior beyond the annotations: a 200-row cap, full-result CSV dumping via output_path, underscore flattening of nested fields (trend.direction -> trend_direction), booleans as 1/0, and the fact that tables live in memory for the server process (so state is ephemeral). However, readOnlyHint=false is not explained in prose even though the description calls the SQL 'read-only' -- the file write from output_path is the likely reason, but the agent must infer it, leaving a mild annotation/description tension rather than a clean contradiction.

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

Conciseness5/5

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

Four dense sentences with no filler; the dialect, allowed statement types, and row cap lead, with encoding and lifetime details trailing. Every clause carries information an agent would otherwise have to discover by trial.

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?

For a SQL execution tool with an output schema already present, this covers the remaining unknowns an agent needs: row limits, escape hatch for full results, field flattening, boolean representation, and that tables are process-scoped and vanish on restart. Nothing material for correct invocation is missing.

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 description coverage is 100%, so the schema already documents all four parameters, and the description largely restates it (output_path = 'full result to a CSV file', the 200-row default matching max_rows). The only added meaning is the tradeoff framing 'for bulk work' versus the row cap; 'format' and the 'One statement' constraint are left to the schema.

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 ('Read-only SQL (SQLite) over tables saved with store_as') and enumerates the accepted statement forms (SELECT, WITH, SHOW TABLES, DESCRIBE <table>). That is far more concrete than a bare 'run a query', but it never distinguishes itself from the sibling 'query' or 'get_schema' tools, which plausibly overlap with the SQL and SHOW TABLES/DESCRIBE surface described here.

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 usable routing context: only SELECT/WITH and the two metadata statements are accepted, and output_path is framed as the escape hatch 'for bulk work' when the 200-row cap would truncate. It stops short of explicit exclusions or pointing at an alternative tool for schema inspection or non-SQL access.

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