Skip to main content
Glama
nulab

Backlog MCP Server

update_version_milestone

Update an existing version milestone's name, dates, or archive status in Backlog.

Instructions

Updates an existing version milestone

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
projectIdNoThe numeric ID of the project (e.g., 12345)
projectKeyNoThe key of the project (e.g., 'PROJECT')
idYesVersion ID
nameYesVersion name
descriptionNoUpdates an existing version milestone
startDateNoStart date
releaseDueDateNoRelease due date
archivedNoArchive status of the version
organizationNoOptional organization name. Use list_organizations to inspect available organizations.

Implementation Reference

  • The handler function for the update_version_milestone tool. It resolves project ID or key, then calls backlog.patchVersions() to update a version milestone.
    export const updateVersionMilestoneTool = (
      backlog: Backlog,
      { t }: TranslationHelper
    ): ToolDefinition<
      ReturnType<typeof updateVersionMilestoneSchema>,
      (typeof VersionSchema)['shape']
    > => {
      return {
        name: 'update_version_milestone',
        description: t(
          'TOOL_UPDATE_VERSION_MILESTONE_DESCRIPTION',
          'Updates an existing version milestone'
        ),
        schema: z.object(updateVersionMilestoneSchema(t)),
        outputSchema: VersionSchema,
        importantFields: [
          'id',
          'name',
          'description',
          'startDate',
          'releaseDueDate',
          'archived',
        ],
        handler: async ({ projectId, projectKey, id, ...params }) => {
          const result = resolveIdOrKey(
            'project',
            { id: projectId, key: projectKey },
            t
          );
          if (!result.ok) {
            throw result.error;
          }
          return backlog.patchVersions(result.value, id, params);
        },
      };
    };
  • Zod schema defining the input parameters for the update_version_milestone tool: projectId, projectKey, id, name, description, startDate, releaseDueDate, archived.
    const updateVersionMilestoneSchema = buildToolSchema((t) => ({
      projectId: z
        .number()
        .optional()
        .describe(
          t(
            'TOOL_UPDATE_VERSION_MILESTONE_PROJECT_ID',
            'The numeric ID of the project (e.g., 12345)'
          )
        ),
      projectKey: z
        .string()
        .optional()
        .describe(
          t(
            'TOOL_UPDATE_VERSION_MILESTONE_PROJECT_KEY',
            "The key of the project (e.g., 'PROJECT')"
          )
        ),
      id: z.number().describe(t('TOOL_UPDATE_VERSION_MILESTONE_ID', 'Version ID')),
      name: z
        .string()
        .describe(t('TOOL_UPDATE_VERSION_MILESTONE_NAME', 'Version name')),
      description: z
        .string()
        .optional()
        .describe(
          t('TOOL_UPDATE_VERSION_MILESTONE_DESCRIPTION', 'Version description')
        ),
      startDate: z
        .string()
        .optional()
        .describe(t('TOOL_UPDATE_VERSION_MILESTONE_START_DATE', 'Start date')),
      releaseDueDate: z
        .string()
        .optional()
        .describe(
          t('TOOL_UPDATE_VERSION_MILESTONE_RELEASE_DUE_DATE', 'Release due date')
        ),
      archived: z
        .boolean()
        .optional()
        .describe(
          t(
            'TOOL_UPDATE_VERSION_MILESTONE_ARCHIVED',
            'Archive status of the version'
          )
        ),
    }));
  • Registration of the update_version_milestone tool in the 'issue' toolset within the allTools collection.
    updateVersionMilestoneTool(backlog, helper),
    deleteVersionTool(backlog, helper),
  • VersionSchema defines the output shape returned by the update_version_milestone tool.
    export const VersionSchema = z.object({
      id: z.number(),
      projectId: z.number(),
      name: z.string(),
      description: z.string().optional(),
      startDate: z.string().optional(),
      releaseDueDate: z.string().optional(),
      archived: z.boolean(),
      displayOrder: z.number(),
    });
  • Helper used by the handler to resolve project identification (by ID or key). The handler calls resolveIdOrKey('project', ...) to get the project identifier before calling patchVersions.
    function resolveIdOrField<E extends EntityName, F extends string>(
      entity: E,
      fieldName: F,
      values: ResolveIdOrFieldInput<F>,
      t: TranslationHelper['t']
    ): ResolveResult {
      const value = tryResolveIdOrField(fieldName, values);
      if (value === undefined) {
        return {
          ok: false,
          error: new Error(
            t(
              `${entity.toUpperCase()}_ID_OR_${fieldName.toUpperCase()}_REQUIRED`,
              `${capitalize(entity)} ID or ${fieldName} is required`
            )
          ),
        };
      }
    
      return { ok: true, value };
    }
    
    function tryResolveIdOrField<F extends string>(
      fieldName: F,
      values: ResolveIdOrFieldInput<F>
    ): string | number | undefined {
      return values.id !== undefined ? values.id : values[fieldName];
    }
    
    export const resolveIdOrKey = <E extends EntityName>(
      entity: E,
      values: { id?: number; key?: string },
      t: TranslationHelper['t']
    ): ResolveResult => resolveIdOrField(entity, 'key', values, t);
    
    export const resolveIdOrName = <E extends EntityName>(
      entity: E,
      values: { id?: number; name?: string },
      t: TranslationHelper['t']
    ): ResolveResult => resolveIdOrField(entity, 'name', values, t);
    
    function capitalize(str: string): string {
      return str.charAt(0).toUpperCase() + str.slice(1);
    }
Behavior2/5

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

No annotations are provided, so the description must disclose behavioral traits. It only says 'Updates', but does not mention permissions, side effects, or behavior changes for mutation.

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, concise sentence that directly conveys the tool's action without unnecessary words.

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 complexity (9 parameters, 2 required) and numerous sibling tools for updates, the description fails to differentiate or provide enough context. No output schema is mentioned.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema description coverage is 100%, many parameter descriptions are generic (e.g., 'Start date', 'Archive status'). The description for the 'description' parameter is a tautology. The tool description adds minimal meaning beyond the schema.

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

Purpose5/5

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

The description clearly states 'Updates an existing version milestone', using a specific verb and resource, and differentiates from siblings like add_version_milestone and get_version_milestone_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?

No guidance on when to use this tool vs alternatives, such as add_version_milestone for creation. No prerequisites or context provided.

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