Skip to main content
Glama
nulab

Backlog MCP Server

get_user_recent_updates

Retrieve activities for a user. Apply optional filters such as activity type, ID range, count, and sort order to customize results.

Instructions

Returns recent updates (activities) for a specific user

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
userIdYesID of the user to retrieve activities for
activityTypeIdNoActivity type IDs to filter by
minIdNoMinimum activity ID
maxIdNoMaximum activity ID
countNoNumber of activities to retrieve (1-100, default: 20)
orderNoSort order ("asc" or "desc", default: "desc")desc
organizationNoOptional organization name. Use list_organizations to inspect available organizations.

Implementation Reference

  • The handler function that executes the tool logic. It calls backlog.getUserActivities() with the provided parameters.
    export const getUserRecentUpdatesTool = (
      backlog: Backlog,
      { t }: TranslationHelper
    ): ToolDefinition<
      ReturnType<typeof getUserRecentUpdatesSchema>,
      (typeof ActivitySchema)['shape']
    > => {
      return {
        name: 'get_user_recent_updates',
        description: t(
          'TOOL_GET_USER_RECENT_UPDATES_DESCRIPTION',
          'Returns recent updates (activities) for a specific user'
        ),
        schema: z.object(getUserRecentUpdatesSchema(t)),
        outputSchema: ActivitySchema,
        importantFields: ['id', 'type', 'content', 'created'],
        handler: async ({ userId, activityTypeId, minId, maxId, count, order }) =>
          backlog.getUserActivities(userId, {
            activityTypeId,
            minId,
            maxId,
            count,
            order,
          }),
      };
    };
  • Input schema definition using Zod. Defines parameters: userId (required number), activityTypeId (optional array of ActivityTypeSchema), minId, maxId, count (1-100, default 20), and order ('asc'/'desc', default 'desc').
    const getUserRecentUpdatesSchema = buildToolSchema((t) => ({
      userId: z
        .number()
        .describe(
          t(
            'TOOL_GET_USER_RECENT_UPDATES_USER_ID',
            'ID of the user to retrieve activities for'
          )
        ),
      activityTypeId: z
        .array(ActivityTypeSchema)
        .optional()
        .describe(
          t(
            'TOOL_GET_USER_RECENT_UPDATES_ACTIVITY_TYPE_ID',
            'Activity type IDs to filter by'
          )
        ),
      minId: z
        .number()
        .optional()
        .describe(t('TOOL_GET_USER_RECENT_UPDATES_MIN_ID', 'Minimum activity ID')),
      maxId: z
        .number()
        .optional()
        .describe(t('TOOL_GET_USER_RECENT_UPDATES_MAX_ID', 'Maximum activity ID')),
      count: z
        .number()
        .min(1)
        .max(100)
        .default(20)
        .optional()
        .describe(
          t(
            'TOOL_GET_USER_RECENT_UPDATES_COUNT',
            'Number of activities to retrieve (1-100, default: 20)'
          )
        ),
      order: z
        .enum(['asc', 'desc'])
        .default('desc')
        .optional()
        .describe(
          t(
            'TOOL_GET_USER_RECENT_UPDATES_ORDER',
            'Sort order ("asc" or "desc", default: "desc")'
          )
        ),
    }));
  • Output schema (ActivitySchema) used as the return type of the tool.
    export const ActivitySchema = z.object({
      id: z.number(),
      project: ProjectSchema,
      type: ActivityTypeSchema,
      content: z.any(),
      notifications: z.array(z.any()),
      createdUser: UserSchema,
      created: z.string(),
    });
  • Registration of getUserRecentUpdatesTool in the 'space' toolset within the allTools function.
      getUserRecentUpdatesTool(backlog, helper),
    ],
  • Import statement registering the tool module.
    import { getUserRecentUpdatesTool } from './getUserRecentUpdates.js';
Behavior2/5

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

Without annotations, the description fails to disclose behavioral traits like pagination behavior or error handling. The description merely states it returns recent updates, leaving the agent to infer details from the schema.

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 a single, concise sentence with no unnecessary words, earning a high score for efficiency.

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 has 7 parameters and no output schema, the minimal description lacks context on what constitutes 'recent', how filtering works, and expected output, leaving significant 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 input schema has 100% description coverage, so the parameters are adequately documented. The tool description adds no extra meaning, meeting the baseline.

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 returns recent updates for a specific user, which distinguishes it from sibling tools like 'get_space_activities'. However, it lacks specificity about the filtering options available.

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 alternatives such as 'get_space_activities' or 'get_issues'. The agent receives no context for tool selection.

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