Skip to main content
Glama
rwese
by rwese

write

Create, update, or list backlog work items to manage tasks with priorities and status tracking. Supports operations like create, amend, approve, and filter by status.

Instructions

Write access to backlog management - create, amend, and list backlog work items

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionNoOperation to perform (default: create)
topicNoTopic name (required for create/amend)
descriptionNoDescription (required for create, optional for amend)
priorityNoPriority level for create/amend operations (default: medium)
statusNoStatus for amend operation or filter for list operation

Implementation Reference

  • Main handler function for the "write" MCP tool. Dispatches to sub-handlers based on the 'action' parameter (create, amend, submit, etc.).
    async function handleBacklogWrite(args: any, context: any) {
      const action = args.action || "create";
    
      switch (action) {
        case "create":
          return await handleCreate(args, context);
        case "list":
          return await listBacklogItems(args);
        case "amend":
          return await handleAmend(args, context);
        case "submit":
          return await handleSubmit(args, context);
        case "approve":
          return await handleApprove(args, context);
        case "reopen":
          return await handleReopen(args, context);
        case "wontfix":
          return await handleWontfix(args, context);
        default:
          throw new Error(`Unknown action: ${action}`);
      }
    }
  • Input schema definition for the "write" tool, specifying parameters like action, topic, description, priority, and status.
    inputSchema: {
      type: "object",
      properties: {
        action: {
          type: "string",
          enum: ["create", "list", "amend", "approve", "submit", "reopen", "wontfix"],
          description: "Operation to perform (default: create)",
        },
        topic: {
          type: "string",
          description: "Topic name (required for create/amend)",
        },
        description: {
          type: "string",
          description: "Description (required for create, optional for amend)",
        },
        priority: {
          type: "string",
          enum: ["high", "medium", "low"],
          description: "Priority level for create/amend operations (default: medium)",
        },
        status: {
          type: "string",
          enum: ["new", "ready", "review", "done", "reopen", "wontfix"],
          description: "Status for amend operation or filter for list operation",
        },
      },
    },
  • src/index.ts:832-833 (registration)
    Handler dispatch registration for the "write" tool in the CallToolRequestSchema switch statement.
    result = await handleBacklogWrite(request.params.arguments, context);
    break;
  • src/index.ts:656-687 (registration)
    Tool metadata and schema registration for "write" in the ListToolsRequestSchema response.
    {
      name: "write",
      description: "Write access to backlog management - create, amend, and list backlog work items",
      inputSchema: {
        type: "object",
        properties: {
          action: {
            type: "string",
            enum: ["create", "list", "amend", "approve", "submit", "reopen", "wontfix"],
            description: "Operation to perform (default: create)",
          },
          topic: {
            type: "string",
            description: "Topic name (required for create/amend)",
          },
          description: {
            type: "string",
            description: "Description (required for create, optional for amend)",
          },
          priority: {
            type: "string",
            enum: ["high", "medium", "low"],
            description: "Priority level for create/amend operations (default: medium)",
          },
          status: {
            type: "string",
            enum: ["new", "ready", "review", "done", "reopen", "wontfix"],
            description: "Status for amend operation or filter for list operation",
          },
        },
      },
    },
  • Example helper function called by the write handler for the 'create' action, handling new backlog item creation.
    async function handleCreate(args: any, context: any) {
      const { topic, description, priority = "medium" } = args;
    
      if (!topic || !description) {
        throw new Error("topic and description are required for create action");
      }
    
      const filename = generateBacklogFilename(topic);
      const backlogDir = getBacklogDir();
      const dirpath = `${backlogDir}/${filename}`;
      const filepath = `${dirpath}/item.md`;
    
       const newExists = await fileExists(filepath);
       const legacyPath = `${backlogDir}/${filename}.md`;
       const legacyExists = await fileExists(legacyPath);
       
       if (newExists || legacyExists) {
         throw new Error(`Backlog item already exists. Use 'amend' to update it.`);
       }
    
       const content = createBacklogTemplate(topic, description, priority, context);
       mkdirSync(dirpath, { recursive: true });
       await writeFile(filepath, content);
      return `Created backlog item: ${filepath}`;
    }
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states 'write access' and lists actions like 'create' and 'amend', implying mutations, but doesn't disclose permissions needed, side effects, error handling, or response format. This is inadequate for a tool with multiple write operations and no structured safety hints.

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, efficient sentence that front-loads the core purpose. It avoids redundancy and wastes no words, though it could be slightly more structured by separating actions from context.

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 tool's complexity (5 parameters, multiple write operations) and lack of annotations and output schema, the description is insufficient. It doesn't explain return values, error conditions, or behavioral nuances, leaving gaps for an AI agent to correctly invoke it in varied scenarios.

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 fully documents all 5 parameters with enums and descriptions. The description adds no parameter-specific information beyond implying actions like 'create' and 'amend', which are already covered in the schema. Baseline 3 is appropriate as the schema handles parameter semantics effectively.

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: 'Write access to backlog management - create, amend, and list backlog work items'. It specifies the verb ('create, amend, and list') and resource ('backlog work items'), making the function understandable. However, it doesn't differentiate from sibling tools like 'todo-write' or 'read', which might handle similar operations in different contexts.

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 no guidance on when to use this tool versus alternatives. It mentions 'write access' but doesn't specify prerequisites, contexts, or exclusions compared to siblings like 'todo-write' or 'read'. Usage is implied through the action list but not explicitly stated.

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/rwese/mcp-backlog'

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