Skip to main content
Glama
Datris MCP Server

Datris MCP Server

query_snowflake

Run read-only Snowflake queries using a pipeline’s configured connection, supporting SELECT, SHOW, and DESCRIBE; omit SQL to preview the destination table.

Instructions

Run a read-only query against the Snowflake account a pipeline loads into. Pass the pipeline name; the server resolves the account, credentials, warehouse, and role from the pipeline's config — same connection the loader uses, credentials never leave the server. Only works for pipelines whose destination is Snowflake (database with useSnowflake=true). Allowed statements: SELECT (WITH/CTE), SHOW, and DESCRIBE — LIMIT is auto-appended to SELECTs. Omit sql to preview the pipeline's destination table (the 'did my load land?' check). Metadata discovery uses the same tool — there are no separate list_snowflake_* tools: SHOW DATABASES, SHOW SCHEMAS IN DATABASE <db>, SHOW TABLES IN SCHEMA <db>.<schema>, DESCRIBE TABLE <db>.<schema>.<table>, or query .information_schema.columns. Queries run on the customer's configured warehouse (which costs them compute) — keep them targeted and let the default LIMIT stand unless the user asks for more.

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": {
      "pipeline": "<pipeline>"
    },
    "name": "query_snowflake"
  }
}

Input Schema

NameRequiredDescriptionDefault
sqlNoRead-only statement: SELECT/WITH, SHOW, or DESCRIBE. Omit to preview the pipeline's destination table.
limitNoMaximum rows to return (default: 100). Pass -1 for unlimited.
pipelineYesPipeline name (from list_pipelines). Must have a Snowflake destination.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does most of it: read-only statement allowlist (SELECT/WITH, SHOW, DESCRIBE), automatic LIMIT appending, server-side credential resolution that never leaves the server, and an explicit cost warning that queries burn the customer's warehouse compute. It stops short of describing failure modes for non-Snowflake pipelines, result shape, or what happens when a disallowed statement is passed, which keeps it below 5.

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?

Front-loads the core action and eligibility in the first two sentences, then moves to statement allowlist, preview behavior, metadata patterns, and cost guidance in descending order of importance. Every sentence contributes a distinct operational fact; nothing is repeated from the schema verbatim.

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 3-parameter read-only tool with no output schema and no annotations, the description supplies everything an agent needs to decide to call it and to construct a valid statement: eligibility gate, allowlist, LIMIT behavior, credential model, and metadata-discovery recipes. Return formatting is the only omission and is low-stakes for a tabular query tool.

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, but the description adds real meaning: omitting `sql` is framed as a deliberate destination-table preview rather than an error, `pipeline` is tied to list_pipelines and the useSnowflake eligibility constraint, and the cost guidance implicitly explains why the default `limit` should be left alone. It does not explain the `limit: -1` interaction with the auto-appended LIMIT, which the schema alone covers.

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?

States a specific verb and resource ('run a read-only query against the Snowflake account') and scopes it to pipelines whose destination is Snowflake. It also explicitly separates itself from would-be siblings by noting there are no separate list_snowflake_* tools, so an agent can distinguish it from query_databricks/query_postgres and from catalog tools without opening a 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?

Gives explicit when-to-use conditions (metadata discovery via SHOW DATABASES / SHOW SCHEMAS / SHOW TABLES / DESCRIBE, and the 'did my load land?' preview when `sql` is omitted), plus a hard eligibility gate (destination must have useSnowflake=true). It even covers the alternative surface (information_schema.columns) and closes off the assumption of dedicated list tools.

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

Deploy Server

Other Tools