Табуля

connections_list

Read-onlyIdempotent

First step for working with databases. Lists the database connections (Postgres, MySQL, ClickHouse, etc.) configured for a Tabulya space. Returns each connection's uuid, name, type, and createdDate. Flow: connections_list → connections_get_schemas (or connections_search_tables for big databases) → use a connection uuid to query its tables. Signature: connections_list(space_uuid?).

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": "connections_list"
  }
}

Input Schema

Name	Required	Description	Default
`space_uuid`	No	UUID of the Tabulya space. Optional — auto-detected when you belong to exactly one space; if you belong to several, the error lists them so you can pass one.

Output Schema

Name	Required	Description	Default
`connections`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 31, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and non-destructive behavior, so the safety profile is covered. The description adds workflow-position behavior and names the exact fields returned (uuid, name, type, createdDate), which helps the agent decide whether it needs connections_get_schemas next. It does not discuss pagination or behavior with many connections, which is the remaining gap.

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?

Front-loaded with purpose, then context, then flow, then signature — a good information hierarchy in three compact sentences. The trailing signature line is largely redundant with the input schema and is the only non-earning element.

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?

An output schema exists, and the description still names the key returned fields. For a single-optional-parameter read tool with full annotations, everything needed to select and invoke it correctly — purpose, prerequisites, next step, and singleton-space behavior — is present.

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 coverage is 100% and the space_uuid property description already explains auto-detection and the multi-space error that lists options. The description only restates optionality via the "connections_list(space_uuid?)" signature, adding no semantics beyond the schema. Baseline 3 is appropriate.

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 ("Lists the database connections") and scopes it to a Tabulya space. It also enumerates concrete examples (Postgres, MySQL, ClickHouse) and the returned fields, so the agent can distinguish it from connections_get_schemas and connections_search_tables without opening any 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 frames the tool as "First step for working with databases" and gives the full call chain: connections_list → connections_get_schemas (or connections_search_tables for big databases) → query using a connection uuid. Both the sequencing and the branch condition for choosing between the two downstream tools are stated, not inferred.

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

All Табуля 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.

Resources

Need Help?