Skip to main content
Glama
dsh-databases

dsh-databases

by nvznc

Guardar conexión

save_connection
Idempotent

Store or replace a named database connection for reuse in list_databases, list_tables, describe_table, run_query, and execute_sql; validate it afterward with test_connection.

Instructions

Guarda (o reemplaza) una conexión con nombre en el archivo de datos del usuario, para luego elegirla con "connection" en list_databases, list_tables, describe_table, run_query y execute_sql. No valida la conexión; usa test_connection después de guardar.

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": {
      "name": "<name>",
      "engine": "<engine>",
      "user": "<user>",
      "password": "<password>"
    },
    "name": "save_connection"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostNoHost o IP (por defecto localhost).
nameYesNombre único, por ejemplo "farmacia-prod" o "core-mysql".
portNoPuerto TCP; si se omite se usa el del motor.
userYesUsuario del motor.
engineYesMotor de la conexión.
optionsNoOpciones del motor: "encrypt", "trustServerCertificate" (mssql), "ssl" (mysql/postgres).
databaseNoBase de datos por defecto de esta conexión.
passwordYesContraseña.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=true, so the safety profile is partly covered. The description adds genuinely new behavior: the write replaces an existing same-named connection (an overwrite with data-loss implications) and performs no connectivity validation. It does not mention where the file lives or what the response looks like, which keeps it below a 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?

Two short sentences, verb and overwrite behavior front-loaded, followed by the downstream consumption pattern and the validation caveat. No filler, and every clause conveys something actionable.

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 an eight-parameter write tool with a nested options object and no output schema, the description covers purpose, downstream use, overwrite semantics and the missing validation step. The only gaps are the return value and whether credentials are stored in plaintext, which are minor for a local save operation.

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% and the schema itself documents all eight parameters including the nested options object and the engine enum, so the schema carries the semantic load. The description adds only the notion that the name is the lookup key used elsewhere, which is marginal beyond that baseline.

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 ("Guarda (o reemplaza) una conexión con nombre en el archivo de datos del usuario") and immediately tells the agent how the saved item is consumed downstream (via the "connection" argument in list_databases, list_tables, describe_table, run_query and execute_sql). This distinguishes it cleanly from test_connection and the list/remove siblings.

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 clear operational guidance: use this to persist a named connection for later reuse, and explicitly routes the agent to test_connection afterward because this tool does not validate. It does not explicitly address when to prefer remove_connection or list_connections, but the alternatives relevant to correct invocation are named.

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