Skip to main content
Glama
kocierik
by kocierik

create-prepared-query

Define prepared queries to efficiently retrieve data from Consul MCP Server, specifying services, nearest nodes, and datacenters for targeted results.

Instructions

Create a new prepared query

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
datacentersNoDatacenters to query
nameNoName of the prepared query
nearestNNoNumber of nearest nodes to return
serviceNoService to query

Implementation Reference

  • The asynchronous handler function that implements the core logic of the 'create-prepared-query' tool by calling consul.query.create to create a prepared query in Consul and handling the response or errors.
    async ({ name, service, nearestN, datacenters }) => {
      try {
        // @ts-ignore - The Consul type definitions are incomplete
        const query = await consul.query.create({
          Name: name,
          Service: {
            Service: service,
            Failover: {
              NearestN: nearestN || 3,
              Datacenters: datacenters || [],
            },
          },
        }) as PreparedQuery;
        return { content: [{ type: "text", text: `Created prepared query: ${query.ID}` }] };
      } catch (error) {
        console.error("Error creating prepared query:", error);
        return { content: [{ type: "text", text: `Error creating prepared query: ${name}` }] };
      }
    }
  • Zod schema defining the input parameters for the 'create-prepared-query' tool, including name, service, nearestN, and datacenters.
    {
      name: z.string().default("").describe("Name of the prepared query"),
      service: z.string().default("").describe("Service to query"),
      nearestN: z.number().optional().describe("Number of nearest nodes to return"),
      datacenters: z.array(z.string()).optional().describe("Datacenters to query"),
    },
  • The server.tool call that registers the 'create-prepared-query' tool with its description, input schema, and handler function.
    server.tool(
      "create-prepared-query",
      "Create a new prepared query",
      {
        name: z.string().default("").describe("Name of the prepared query"),
        service: z.string().default("").describe("Service to query"),
        nearestN: z.number().optional().describe("Number of nearest nodes to return"),
        datacenters: z.array(z.string()).optional().describe("Datacenters to query"),
      },
      async ({ name, service, nearestN, datacenters }) => {
        try {
          // @ts-ignore - The Consul type definitions are incomplete
          const query = await consul.query.create({
            Name: name,
            Service: {
              Service: service,
              Failover: {
                NearestN: nearestN || 3,
                Datacenters: datacenters || [],
              },
            },
          }) as PreparedQuery;
          return { content: [{ type: "text", text: `Created prepared query: ${query.ID}` }] };
        } catch (error) {
          console.error("Error creating prepared query:", error);
          return { content: [{ type: "text", text: `Error creating prepared query: ${name}` }] };
        }
      }
    );
  • TypeScript interface defining the structure of a PreparedQuery response from Consul, used in the tool's handler.
    interface PreparedQuery {
      ID: string;
      Name: string;
      Service: {
        Service: string;
        Failover: {
          NearestN: number;
          Datacenters: string[];
        };
      };
    }

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, and the description does not disclose any behavioral traits such as idempotency, side effects, or authorization needs. It only states the basic action without context on what 'create' entails.

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?

The description is a single concise sentence, efficiently stating the tool's action. However, it may be overly brief for a creation tool with no output schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of creating a prepared query with four parameters and no output schema, the description is insufficient. It does not explain what a prepared query is, what the tool returns, or any important constraints.

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 input schema already documents all four parameters. The description adds no additional meaning beyond what is already in the schema, which earns a baseline score of 3.

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?

Description states 'Create a new prepared query', which is a clear verb+resource combination. It distinguishes from sibling 'execute-prepared-query' by using 'create' vs 'execute'. However, it is somewhat tautological as it restates the tool name without further detail.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like 'execute-prepared-query' or other create tools. No when-not or prerequisite information provided.

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