Skip to main content
Glama
hichana

Goal Story MCP Server

by hichana

goalstory_create_steps

Break down goals into clear, actionable steps through structured discussion, then present them for review to ensure they're achievable before saving.

Instructions

Formulate actionable steps for a goal through thoughtful discussion. Present the steps for user review either before or after saving, ensuring they're clear and achievable. Confirm if any refinements are needed. IMPORTANT: Steps are ordered by their 'order_ts' timestamp in ascending order - the step with the earliest timestamp becomes step 1, and steps with later timestamps follow in sequence. The first item in your array will receive the earliest timestamp (becoming step 1), and subsequent items will receive progressively later timestamps. NOTE: Array order determines step sequence - first array item = step 1, second array item = step 2, etc.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
goal_idYesUnique identifier of the goal these steps will help achieve.
stepsYesList of clear, actionable step descriptions in sequence. The first item in this array will become step 1, the second will become step 2, and so on based on timestamp ordering.

Implementation Reference

  • The execution handler for the 'goalstory_create_steps' tool. It handles input args, converts steps if string (for local dev), makes POST to /steps endpoint, and returns formatted response with note on ordering.
    async (args) => {
      const url = `${GOALSTORY_API_BASE_URL}/steps`;
    
      // when developing locally, we can pass in a list of strings in the MCP
      // inspector like this: step1, step2
      let steps = args.steps;
      if (typeof steps === "string") {
        const itemsAreAString = steps as string;
        steps = itemsAreAString
          .split(",")
          .map((s) => s.trim())
          .filter((s) => s.length > 0);
      }
    
      const body = {
        goal_id: args.goal_id,
        steps,
      };
    
      const result = await doRequest(url, "POST", body);
      return {
        content: [
          {
            type: "text",
            text: `Steps created:\n${JSON.stringify(result, null, 2)}\n\nNOTE: Steps are ordered by their 'order_ts' timestamp in ascending order - the step with the smallest timestamp value (updated first) is step 1. The steps appear in order, with the first step having the smallest timestamp. Example: If step A has timestamp 12:00 and step B has timestamp 12:01, then step A is step 1 and step B is step 2.`,
          },
        ],
        isError: false,
      };
    },
  • Tool definition including name, description, and Zod input schema for validating goal_id (string) and steps (array of strings). Used in registration.
    export const CREATE_STEPS_TOOL = {
      name: "goalstory_create_steps",
      description: `Formulate actionable steps for a goal through thoughtful discussion. Present the steps for user review either before or after saving, ensuring they're clear and achievable. Confirm if any refinements are needed. IMPORTANT: Steps are ordered by their 'order_ts' timestamp in ascending order - the step with the earliest timestamp becomes step 1, and steps with later timestamps follow in sequence. The first item in your array will receive the earliest timestamp (becoming step 1), and subsequent items will receive progressively later timestamps. NOTE: Array order determines step sequence - first array item = step 1, second array item = step 2, etc.`,
      inputSchema: z.object({
        goal_id: z
          .string()
          .describe("Unique identifier of the goal these steps will help achieve."),
        steps: z
          .array(z.string())
          .describe(
            "List of clear, actionable step descriptions in sequence. The first item in this array will become step 1, the second will become step 2, and so on based on timestamp ordering.",
          ),
      }),
    };
  • src/index.ts:445-479 (registration)
    MCP server registration of the tool using server.tool() with name from CREATE_STEPS_TOOL, description, inputSchema.shape, and custom handler function.
    server.tool(
      CREATE_STEPS_TOOL.name,
      CREATE_STEPS_TOOL.description,
      CREATE_STEPS_TOOL.inputSchema.shape,
      async (args) => {
        const url = `${GOALSTORY_API_BASE_URL}/steps`;
    
        // when developing locally, we can pass in a list of strings in the MCP
        // inspector like this: step1, step2
        let steps = args.steps;
        if (typeof steps === "string") {
          const itemsAreAString = steps as string;
          steps = itemsAreAString
            .split(",")
            .map((s) => s.trim())
            .filter((s) => s.length > 0);
        }
    
        const body = {
          goal_id: args.goal_id,
          steps,
        };
    
        const result = await doRequest(url, "POST", body);
        return {
          content: [
            {
              type: "text",
              text: `Steps created:\n${JSON.stringify(result, null, 2)}\n\nNOTE: Steps are ordered by their 'order_ts' timestamp in ascending order - the step with the smallest timestamp value (updated first) is step 1. The steps appear in order, with the first step having the smallest timestamp. Example: If step A has timestamp 12:00 and step B has timestamp 12:01, then step A is step 1 and step B is step 2.`,
            },
          ],
          isError: false,
        };
      },
    );
  • TypeScript interface defining the input shape for the tool, matching the Zod schema.
    export interface GoalstoryCreateStepsInput {
      goal_id: string;
      steps: string[];
    }
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It discloses key behavioral traits: steps are ordered by 'order_ts' timestamp in ascending order, array order determines sequence, and the tool involves user interaction (review and confirmation). However, it lacks details on permissions, rate limits, or what happens if steps are saved (e.g., creation vs. draft state), leaving gaps for a mutation tool.

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

Conciseness3/5

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

The description is moderately concise but could be more front-loaded. The first sentence states the purpose, but subsequent sentences mix usage notes and technical details (e.g., timestamp ordering), making it slightly verbose. It earns its place by covering multiple aspects, but the structure could be improved for clarity, such as separating purpose from behavioral instructions.

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

Completeness3/5

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

Given the tool has no annotations and no output schema, the description provides decent context for a mutation tool with 2 parameters. It covers the creation process, ordering logic, and user interaction, but lacks information on return values, error handling, or prerequisites (e.g., goal existence). This leaves some gaps in completeness for effective agent use.

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 both parameters ('goal_id' and 'steps') well. The description adds some semantic context by emphasizing that steps should be 'clear and achievable' and that array order maps to step sequence, but this mostly reiterates schema details without significant extra meaning. Baseline 3 is appropriate given high schema coverage.

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?

The description clearly states the tool's purpose: 'Formulate actionable steps for a goal through thoughtful discussion.' It specifies the verb ('formulate') and resource ('actionable steps for a goal'), making it easy to understand. However, it doesn't explicitly differentiate from sibling tools like 'goalstory_set_steps_order' or 'goalstory_update_step', which also involve steps, so it misses full sibling distinction.

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?

The description provides some context about presenting steps for user review and confirming refinements, but it doesn't offer explicit guidance on when to use this tool versus alternatives. For example, it doesn't compare to 'goalstory_set_steps_order' for ordering steps or 'goalstory_update_step' for modifying steps, leaving the agent without clear usage boundaries.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hichana/goalstory-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server