Skip to main content
Glama
Frihet-io

Frihet MCP Server

Create Client

create_client

Add new clients to the Frihet MCP Server for generating invoices and quotes. Provide client name and optional contact details to create customer records.

Instructions

Create a new client/customer. Requires at minimum a name. Clients are used when creating invoices and quotes. / Crea un nuevo cliente. Requiere como minimo un nombre. Los clientes se usan al crear facturas y presupuestos.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesClient/company name / Nombre del cliente o empresa
emailNoEmail address / Correo electronico
phoneNoPhone number / Telefono
taxIdNoTax ID (NIF/CIF/VAT) / NIF o CIF
addressNoClient address / Direccion del cliente

Implementation Reference

  • The handler function for the 'create_client' tool that executes the tool logic - receives input, calls client.createClient(), and returns the formatted result
    async (input) => {
      try {
        const result = await client.createClient(input);
        return {
          content: [{ type: "text", text: formatRecord("Client created", result) }],
        };
      } catch (error) {
        return handleToolError(error);
      }
    },
  • Tool registration for 'create_client' including the tool name, title, description, annotations, and inputSchema with Zod validation for name, email, phone, taxId, and address fields
    server.registerTool(
      "create_client",
      {
        title: "Create Client",
        description:
          "Create a new client/customer. Requires at minimum a name. " +
          "Clients are used when creating invoices and quotes. " +
          "/ Crea un nuevo cliente. Requiere como minimo un nombre. " +
          "Los clientes se usan al crear facturas y presupuestos.",
        annotations: CREATE_ANNOTATIONS,
        inputSchema: {
          name: z.string().describe("Client/company name / Nombre del cliente o empresa"),
          email: z.string().optional().describe("Email address / Correo electronico"),
          phone: z.string().optional().describe("Phone number / Telefono"),
          taxId: z.string().optional().describe("Tax ID (NIF/CIF/VAT) / NIF o CIF"),
          address: addressSchema,
        },
      },
  • TypeScript type definition for CreateClientInput - requires 'name' and optionally allows email, phone, taxId, and address fields
    export type CreateClientInput = Pick<Client, "name"> &
      Partial<Pick<Client, "email" | "phone" | "taxId" | "address">>;
  • The FrihetClient.createClient method that makes the actual HTTP POST request to '/clients' endpoint
    async createClient(data: Record<string, unknown>): Promise<Record<string, unknown>> {
      return this.request("POST", "/clients", data);
    }
  • Interface definition for createClient method in IFrihetClient - defines the contract that both local and remote client implementations must satisfy
    createClient(data: Record<string, unknown>): Promise<Record<string, unknown>>;
Behavior3/5

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

Annotations already cover key traits: readOnlyHint=false (write operation), destructiveHint=false (non-destructive). The description adds minimal behavioral context beyond this: it states the minimum requirement ('Requires at minimum a name') and mentions the entity's purpose. However, it doesn't disclose important behavioral aspects like whether duplicate names are allowed, what permissions are needed, or what the response contains.

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

Conciseness3/5

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

The description is appropriately brief (two sentences plus bilingual repetition) and front-loaded with the core purpose. However, the bilingual format creates redundancy without adding new information, slightly reducing efficiency. Every sentence earns its place in one language but not both.

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?

For a creation tool with no output schema and moderate complexity (5 parameters including nested objects), the description is adequate but incomplete. It covers the purpose and minimum requirement but lacks details on what happens after creation (e.g., returns client ID), error conditions, or relationship to other tools. The annotations help but don't fully compensate for missing output information.

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 parameters well-documented in the schema itself. The description adds only one piece of parameter semantics: 'Requires at minimum a name' clarifies that 'name' is the only required field. This is useful but minimal additional value beyond the comprehensive schema documentation.

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 the tool's purpose: 'Create a new client/customer' with the specific resource 'client'. It distinguishes this from siblings like 'update_client' (modification) and 'delete_client' (removal) by specifying creation of a new entity. The bilingual format reinforces but doesn't dilute the core purpose.

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 provides clear context for when to use this tool: 'Clients are used when creating invoices and quotes' explains the downstream purpose. However, it doesn't explicitly state when NOT to use it (e.g., vs. 'update_client' for existing clients) or name specific alternatives among siblings, missing full differentiation.

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/Frihet-io/frihet-mcp'

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