Skip to main content
Glama
topotal

Waroom MCP

by topotal

waroom_get_incidents

Retrieve incident lists from Waroom MCP with filtering options for service, status, severity, date range, and root cause analysis.

Instructions

インシデントの一覧を取得します。各種フィルター条件を指定できます。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNo取得するページ番号(1以上の整数)。デフォルト: 1
per_pageNo1ページあたりの取得数(1-100)。デフォルト: 50
service_namesNoフィルタリング対象のサービス名の配列
statusNoインシデントステータス(resolved, close, detected, investigating, fixing)
root_causeNo根本原因
severitiesNo重要度の配列(critical, high, low, info, unknown)
fromNo開始日(YYYY-MM-DD形式 例: 2023-01-01)
toNo終了日(YYYY-MM-DD形式 例: 2023-12-31)
includes_experimentalNo実験的なインシデントを含めるかどうか
label_namesNoフィルタリング対象のラベル名の配列
commander_idNoコマンダーのID(正の整数)

Implementation Reference

  • Registration of the 'waroom_get_incidents' MCP tool, including input schema (Zod), description, and inline handler function that calls WaroomClient.getIncidents and returns formatted response.
    server.tool(
      'waroom_get_incidents',
      'インシデントの一覧を取得します。各種フィルター条件を指定できます。',
      {
        page: z.number().int().min(1).optional().describe('取得するページ番号(1以上の整数)。デフォルト: 1'),
        per_page: z.number().int().min(1).max(100).optional().describe('1ページあたりの取得数(1-100)。デフォルト: 50'),
        service_names: z.array(z.string().min(1)).min(1).optional().describe('フィルタリング対象のサービス名の配列'),
        status: z.enum(['resolved', 'close', 'detected', 'investigating', 'fixing']).optional().describe('インシデントステータス(resolved, close, detected, investigating, fixing)'),
        root_cause: z.enum(['unspecified', 'code_bug', 'configuration_error', 'deployment_failure', 'infrastructure_failure', 'operational_failure', 'third_party_outage', 'other']).optional().describe('根本原因'),
        severities: z.array(z.enum(['critical', 'high', 'low', 'info', 'unknown'])).min(1).optional().describe('重要度の配列(critical, high, low, info, unknown)'),
        from: z.string().regex(/^\d{4}-\d{2}-\d{2}$/).optional().describe('開始日(YYYY-MM-DD形式 例: 2023-01-01)'),
        to: z.string().regex(/^\d{4}-\d{2}-\d{2}$/).optional().describe('終了日(YYYY-MM-DD形式 例: 2023-12-31)'),
        includes_experimental: z.boolean().optional().describe('実験的なインシデントを含めるかどうか'),
        label_names: z.array(z.string().min(1)).min(1).optional().describe('フィルタリング対象のラベル名の配列'),
        commander_id: z.number().int().positive().optional().describe('コマンダーのID(正の整数)'),
      },
      async (params) => {
        try {
          const { page = 1, per_page = 50, ...filters } = params;
          const response = await waroomClient.getIncidents(page, per_page, filters);
          return {
            content: [{
              type: 'text',
              text: JSON.stringify(response, null, 2)
            }]
          };
        } catch (error) {
          return {
            content: [{
              type: 'text',
              text: `インシデント一覧の取得に失敗しました: ${error}`
            }]
          };
        }
      }
    );
  • WaroomClient.getIncidents helper method: constructs query parameters from filters and makes API call to fetch paginated list of incidents with applied filters.
    async getIncidents(page = 1, perPage = 50, filters: any = {}) {
      try {
        const params: any = { page, per_page: perPage };
        
        // フィルターパラメーターを追加
        if (filters.service_names?.length) params.service_names = filters.service_names.join(',');
        if (filters.status) params.status = filters.status;
        if (filters.root_cause) params.root_cause = filters.root_cause;
        if (filters.severities?.length) params.severities = filters.severities.join(',');
        if (filters.from) params.from = filters.from;
        if (filters.to) params.to = filters.to;
        if (filters.includes_experimental !== undefined) params.includes_experimental = filters.includes_experimental;
        if (filters.label_names?.length) params.label_names = filters.label_names.join(',');
        if (filters.commander_id) params.commander_id = filters.commander_id;
    
        const response = await this.axiosInstance.get(`${this.baseUrl}/incidents`, { params });
        return response.data;
      } catch (error) {
        throw new Error(`Failed to get incidents: ${error}`);
      }
  • src/main.ts:26-29 (registration)
    Top-level invocation of createIncidentsTools (among others) to register all incident-related tools, including waroom_get_incidents, to the MCP server.
    createIncidentsTools(server, waroomClient);
    createPostmortemsTools(server, waroomClient);
    createServicesTools(server, waroomClient);
    createLabelsTools(server, waroomClient);
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions filtering capability but doesn't describe important behavioral aspects: whether this is a read-only operation, if it requires authentication, what the return format looks like (list structure, fields included), pagination behavior beyond the parameters, rate limits, or error conditions. For a list retrieval tool with 11 parameters, this leaves significant gaps in understanding how the tool behaves.

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 - just two short Japanese sentences that communicate the core functionality efficiently. Every word earns its place: the first sentence states the primary purpose, the second adds the filtering capability. There's no redundancy or unnecessary elaboration.

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?

For a tool with 11 parameters, no annotations, and no output schema, the description is insufficiently complete. It doesn't address the tool's behavioral characteristics, return format, error handling, or relationship to sibling tools. While the schema documents parameters well, the description fails to provide the contextual understanding needed for effective tool selection and invocation in a complex incident management system.

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%, with all 11 parameters well-documented in the schema itself. The description adds minimal value beyond the schema by mentioning that various filter conditions can be specified, but doesn't provide additional context about parameter relationships, typical usage patterns, or semantic meaning beyond what's already in the parameter descriptions. This meets the baseline for 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 verb ('取得します' - get/retrieve) and resource ('インシデントの一覧' - list of incidents), making the purpose immediately understandable. It also mentions filtering capability ('各種フィルター条件を指定できます' - various filter conditions can be specified), which adds specificity. However, it doesn't explicitly differentiate from sibling tools like 'waroom_get_incident_details' which gets details of a specific incident rather than a filtered list.

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 doesn't mention sibling tools like 'waroom_get_incident_details' for single incidents or 'waroom_get_postmortems' for related data. There's no indication of prerequisites, dependencies, or typical use cases beyond the basic functionality 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/topotal/waroom-mcp'

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