Skip to main content
Glama
nulab

Backlog MCP Server

reset_unread_notification_count

Resets the count of unread notifications to zero, clearing the notification badge for the user's account.

Instructions

Reset unread notification count

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
organizationNoOptional organization name. Use list_organizations to inspect available organizations.

Implementation Reference

  • Main handler implementation of the 'reset_unread_notification_count' tool. Defines the tool schema (no input params), registers the tool name/description, and the handler calls backlog.resetNotificationsMarkAsRead(). Output uses NotificationCountSchema.
    import { z } from 'zod';
    import { Backlog } from 'backlog-js';
    import { buildToolSchema, ToolDefinition } from '../types/tool.js';
    import { TranslationHelper } from '../createTranslationHelper.js';
    import { NotificationCountSchema } from '../types/zod/backlogOutputDefinition.js';
    
    const resetUnreadNotificationCountSchema = buildToolSchema((_t) => ({}));
    
    export const resetUnreadNotificationCountTool = (
      backlog: Backlog,
      { t }: TranslationHelper
    ): ToolDefinition<
      ReturnType<typeof resetUnreadNotificationCountSchema>,
      (typeof NotificationCountSchema)['shape']
    > => {
      return {
        name: 'reset_unread_notification_count',
        description: t(
          'TOOL_RESET_UNREAD_NOTIFICATION_COUNT_DESCRIPTION',
          'Reset unread notification count'
        ),
        schema: z.object(resetUnreadNotificationCountSchema(t)),
        outputSchema: NotificationCountSchema,
        handler: async () => backlog.resetNotificationsMarkAsRead(),
      };
    };
  • Import of resetUnreadNotificationCountTool from its module file.
    import { resetUnreadNotificationCountTool } from './resetUnreadNotificationCount.js';
  • Registration of resetUnreadNotificationCountTool in the 'notifications' toolset group.
    resetUnreadNotificationCountTool(backlog, helper),
  • NotificationCountSchema definition used as the output schema for the tool: { count: z.number() }.
    export const NotificationCountSchema = z.object({
      count: z.number(),
    });
  • ToolDefinition type and buildToolSchema helper used by the tool implementation.
    export type ToolDefinition<
      Shape extends z.ZodRawShape,
      OutputShape extends z.ZodRawShape,
    > = {
      name: string;
      description: string;
      schema: z.ZodObject<Shape>;
      outputSchema: z.ZodObject<OutputShape>;
      handler: (
        input: z.infer<z.ZodObject<Shape>> & {
          fields?: string;
          organization?: string;
        }
      ) => Promise<
        z.infer<z.ZodObject<OutputShape>> | z.infer<z.ZodObject<OutputShape>>[]
      >;
      importantFields?: (keyof z.infer<z.ZodObject<OutputShape>>)[];
    };
    
    export const buildToolSchema = <T extends z.ZodRawShape>(
      fn: (t: TranslationHelper['t']) => T
    ) => fn;
Behavior2/5

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

With no annotations, the description must fully disclose behavior, but it only states the action without explaining effects (e.g., does it mark notifications as read? what happens to the count? does it require authentication?). The ambiguity about scope (user or organization) further reduces transparency.

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

Conciseness2/5

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

The description is extremely short (5 words) and essentially restates the tool name, which is under-specification rather than concise. It lacks necessary details to be useful, making it insufficient despite no verbose language.

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 presence of multiple notification-related siblings, the description fails to provide enough context for an agent to choose this tool. No output schema means the return value is unknown, and the description does not mention use cases or typical results.

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 input schema provides full coverage (100%) with a clear description for the organization parameter. The tool description adds no additional meaning beyond the schema, so it meets the baseline of 3 for high coverage, but does not exceed it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the verb 'reset' and resource 'unread notification count', which clearly indicates the action on a specific metric. However, it lacks scope detail (e.g., user vs. organization) and does not distinguish from similar tools like mark_notification_as_read, which marks individual notifications rather than resetting the count.

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 is provided on when to use this tool versus its siblings (e.g., mark_notification_as_read, count_notifications). The description does not mention prerequisites, such as having read all notifications, or situations where resetting the count is appropriate.

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/nulab/backlog-mcp-server'

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