Skip to main content
Glama

backlog_update

Modify existing backlog items by updating their title, status, parent relationships, due dates, or completion evidence to reflect current progress and requirements.

Instructions

Update an existing item. For editing the markdown body, use write_resource with str_replace.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesTask ID to update
titleNoNew title
statusNoNew status
epic_idNoParent epic ID (null to unlink)
parent_idNoParent ID (null to unlink). Takes precedence over epic_id.
blocked_reasonNoReason if status is blocked
evidenceNoProof of completion when marking done - links to PRs, docs, or notes
referencesNoReference links. Formats: external URLs (https://...), task refs (mcp://backlog/tasks/TASK-XXXX.md), resources (mcp://backlog/resources/{path}). Local files must include extension (file:///path/to/file.md)
due_dateNoDue date for milestones (ISO 8601). Null to clear.
content_typeNoContent type for artifacts (e.g. text/markdown). Null to clear.

Implementation Reference

  • Core handler function that executes the backlog_update tool logic. Retrieves the task, updates fields (handling parent_id/epic_id precedence, nullable fields), applies updates, saves to storage, and returns success/error response.
    async ({ id, epic_id, parent_id, due_date, content_type, ...updates }) => {
      const task = storage.get(id);
      if (!task) return { content: [{ type: 'text', text: `Task ${id} not found` }], isError: true };
    
      // parent_id takes precedence over epic_id
      if (parent_id !== undefined) {
        if (parent_id === null) {
          delete task.parent_id;
          delete task.epic_id;
        } else {
          task.parent_id = parent_id;
        }
      } else if (epic_id !== undefined) {
        if (epic_id === null) {
          delete task.epic_id;
          delete task.parent_id;
        } else {
          task.epic_id = epic_id;
          task.parent_id = epic_id;
        }
      }
    
      // Nullable type-specific fields: null clears, string sets
      for (const [key, val] of Object.entries({ due_date, content_type })) {
        if (val === null) delete (task as any)[key];
        else if (val !== undefined) (task as any)[key] = val;
      }
    
      Object.assign(task, updates, { updated_at: new Date().toISOString() });
      storage.save(task);
      return { content: [{ type: 'text', text: `Updated ${id}` }] };
    }
  • Zod input schema definition for the backlog_update tool, validating parameters including id, title, status, epic_id, parent_id, blocked_reason, evidence, references, due_date, and content_type.
    inputSchema: z.object({
      id: z.string().describe('Task ID to update'),
      title: z.string().optional().describe('New title'),
      status: z.enum(STATUSES).optional().describe('New status'),
      epic_id: z.union([z.string(), z.null()]).optional().describe('Parent epic ID (null to unlink)'),
      parent_id: z.union([z.string(), z.null()]).optional().describe('Parent ID (null to unlink). Takes precedence over epic_id.'),
      blocked_reason: z.array(z.string()).optional().describe('Reason if status is blocked'),
      evidence: z.array(z.string()).optional().describe('Proof of completion when marking done - links to PRs, docs, or notes'),
      references: z.array(z.object({ url: z.string(), title: z.string().optional() })).optional().describe('Reference links. Formats: external URLs (https://...), task refs (mcp://backlog/tasks/TASK-XXXX.md), resources (mcp://backlog/resources/{path}). Local files must include extension (file:///path/to/file.md)'),
      due_date: z.union([z.string(), z.null()]).optional().describe('Due date for milestones (ISO 8601). Null to clear.'),
      content_type: z.union([z.string(), z.null()]).optional().describe('Content type for artifacts (e.g. text/markdown). Null to clear.'),
    }),
  • Tool registration function that registers the backlog_update tool with the MCP server, including description, input schema, and handler callback.
    export function registerBacklogUpdateTool(server: McpServer) {
      server.registerTool(
        'backlog_update',
        {
          description: 'Update an existing item. For editing the markdown body, use write_resource with str_replace.',
          inputSchema: z.object({
            id: z.string().describe('Task ID to update'),
            title: z.string().optional().describe('New title'),
            status: z.enum(STATUSES).optional().describe('New status'),
            epic_id: z.union([z.string(), z.null()]).optional().describe('Parent epic ID (null to unlink)'),
            parent_id: z.union([z.string(), z.null()]).optional().describe('Parent ID (null to unlink). Takes precedence over epic_id.'),
            blocked_reason: z.array(z.string()).optional().describe('Reason if status is blocked'),
            evidence: z.array(z.string()).optional().describe('Proof of completion when marking done - links to PRs, docs, or notes'),
            references: z.array(z.object({ url: z.string(), title: z.string().optional() })).optional().describe('Reference links. Formats: external URLs (https://...), task refs (mcp://backlog/tasks/TASK-XXXX.md), resources (mcp://backlog/resources/{path}). Local files must include extension (file:///path/to/file.md)'),
            due_date: z.union([z.string(), z.null()]).optional().describe('Due date for milestones (ISO 8601). Null to clear.'),
            content_type: z.union([z.string(), z.null()]).optional().describe('Content type for artifacts (e.g. text/markdown). Null to clear.'),
          }),
        },
  • Registration call in the tools index that invokes registerBacklogUpdateTool to register the backlog_update tool with the server.
    registerBacklogUpdateTool(server);
  • STATUSES constant and Status type definition used by the backlog_update schema to validate the status field (values: open, in_progress, blocked, done, cancelled).
    export const STATUSES = ['open', 'in_progress', 'blocked', 'done', 'cancelled'] as const;
    export type Status = (typeof STATUSES)[number];
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. While 'Update an existing item' implies a mutation operation, the description lacks details on permissions needed, whether updates are reversible, rate limits, error conditions, or what happens to unspecified fields (e.g., partial updates). For a mutation tool with 10 parameters and no annotations, this is insufficient.

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?

The description is extremely concise and front-loaded: the first sentence states the core purpose, and the second provides critical usage guidance. Every sentence earns its place with zero waste, making it easy for an agent to parse quickly.

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 complexity (10 parameters, mutation operation) and lack of annotations or output schema, the description is incomplete. It covers purpose and a key usage distinction but omits behavioral details (e.g., side effects, error handling) and output expectations. However, the high schema coverage and explicit sibling guidance partially compensate, making it minimally viable but with clear gaps.

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?

The schema description coverage is 100%, so all parameters are documented in the schema. The description adds no parameter-specific information beyond what the schema provides (e.g., no examples, formatting tips, or constraints). The baseline score of 3 reflects adequate coverage by the schema alone, with no added value from the description.

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: 'Update an existing item.' It specifies the verb ('update') and resource ('existing item'), distinguishing it from sibling tools like backlog_create (create) and backlog_delete (delete). However, it doesn't explicitly differentiate from backlog_context or backlog_get, which are read operations, though 'update' implies mutation.

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?

The description provides explicit guidance on when NOT to use this tool: 'For editing the markdown body, use write_resource with str_replace.' This clearly distinguishes it from the sibling tool write_resource for markdown editing, helping the agent choose the correct alternative for specific update scenarios.

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/gkoreli/backlog-mcp'

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