Skip to main content
Glama
moneyforward-i

Admina MCP Server

update_device_meta

Assign or unassign devices to people, update their status (defaults to 'active' when assigned), location, and assignment dates. Unassigned devices require 'in_stock' or 'decommissioned' status.

Instructions

Update device's meta information including assignment info (peopleId, status, dates) and location. Use this to assign/unassign devices to people. When unassigned, status should be 'in_stock' or 'decommissioned'. When assigned without status, defaults to 'active'.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
deviceIdYesThe ID of the device to update
statusNoDevice status. If 'in_stock' or 'decommissioned', device will be unassigned and assignment dates cleared
peopleIdNoPeople ID to assign device to. Set to null to unassign. Cannot assign if status is 'in_stock' or 'decommissioned'
assignmentStartDateNoAssignment start date (YYYY-MM-DD). Cannot set if status is 'in_stock' or 'decommissioned'
assignmentEndDateNoAssignment end date (YYYY-MM-DD). Cannot set if status is 'in_stock' or 'decommissioned'
location1NoPrimary location information
location2NoSecondary location information

Implementation Reference

  • The main handler function for the update_device_meta tool. It builds a request body from the provided fields and calls the PATCH API endpoint /devices/{deviceId}/meta.
    export async function updateDeviceMeta(params: UpdateDeviceMetaParams) {
      const client = getClient();
    
      const body: Record<string, unknown> = {};
    
      if (params.status !== undefined) body.status = params.status;
      if (params.peopleId !== undefined) body.peopleId = params.peopleId;
      if (params.assignmentStartDate !== undefined) body.assignmentStartDate = params.assignmentStartDate;
      if (params.assignmentEndDate !== undefined) body.assignmentEndDate = params.assignmentEndDate;
      if (params.location1 !== undefined) body.location1 = params.location1;
      if (params.location2 !== undefined) body.location2 = params.location2;
    
      return client.makePatchApiCall(`/devices/${params.deviceId}/meta`, body);
    }
  • Zod validation schema defining the input parameters for update_device_meta: deviceId (required), status, peopleId, assignmentStartDate, assignmentEndDate, location1, location2.
    export const UpdateDeviceMetaSchema = z.object({
      deviceId: z.number().describe("The ID of the device to update"),
      status: z
        .enum(["in_stock", "pre_use", "active", "missing", "malfunction", "decommissioned", "on_order"])
        .optional()
        .describe(
          "Device status. If 'in_stock' or 'decommissioned', device will be unassigned and assignment dates cleared",
        ),
      peopleId: z
        .number()
        .nullable()
        .optional()
        .describe(
          "People ID to assign device to. Set to null to unassign. Cannot assign if status is 'in_stock' or 'decommissioned'",
        ),
      assignmentStartDate: z
        .string()
        .nullable()
        .optional()
        .describe("Assignment start date (YYYY-MM-DD). Cannot set if status is 'in_stock' or 'decommissioned'"),
      assignmentEndDate: z
        .string()
        .nullable()
        .optional()
        .describe("Assignment end date (YYYY-MM-DD). Cannot set if status is 'in_stock' or 'decommissioned'"),
      location1: z.string().optional().describe("Primary location information"),
      location2: z.string().optional().describe("Secondary location information"),
    });
  • src/index.ts:130-134 (registration)
    Tool registration in the ListToolsRequestSchema handler: defines the tool name 'update_device_meta' with its description and JSON schema.
    {
      name: "update_device_meta",
      description:
        "Update device's meta information including assignment info (peopleId, status, dates) and location. Use this to assign/unassign devices to people. When unassigned, status should be 'in_stock' or 'decommissioned'. When assigned without status, defaults to 'active'.",
      inputSchema: zodToJsonSchema(UpdateDeviceMetaSchema),
  • src/index.ts:302-302 (registration)
    Tool handler map entry: links the tool name 'update_device_meta' to its handler function updateDeviceMeta with schema validation via parse.
    update_device_meta: async (input) => updateDeviceMeta(UpdateDeviceMetaSchema.parse(input)),
Behavior4/5

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

With no annotations, the description carries the full burden. It discloses that setting status to in_stock or decommissioned will unassign and clear dates, and that assigning without status defaults to active. This is good coverage of key side effects. However, it does not mention whether location updates are independent, or what happens to other fields if omitted.

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 three short sentences with no filler. Every sentence adds distinct information: what is updated, how to use for assignment, and default behavior. It is front-loaded with the main purpose.

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 no output schema and 7 parameters, the description explains key parameter interactions but omits the return value (likely the updated device object or success indicator). It also does not mention error conditions, permissions, or that only the specified fields are updated. While the core logic is covered, the missing return and error context make it less complete.

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

Parameters4/5

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

Schema coverage is 100%, baseline 3. The description adds narrative meaning beyond the schema, such as the default status behavior and the interplay between status and assignment. This helps the agent understand the logical constraints not fully captured in the schema descriptions alone.

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 it updates device meta information including assignment and location. It specifies 'update' as the verb and 'device meta information' as the resource. However, it does not explicitly differentiate from the sibling tool 'update_device', which updates device attributes. The name 'update_device_meta' provides some distinction, but the description could be more precise.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use this to assign/unassign devices to people', providing clear guidance on when to use this tool. It also gives conditional logic for status and assignment, like 'When unassigned, status should be in_stock or decommissioned' and 'When assigned without status, defaults to active'. No mention of alternatives or when not to use compared to update_device.

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/moneyforward-i/admina-mcp-server'

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