Skip to main content
Glama

create_table

Creates a new table in an Airtable base with default fields and returns the generated table ID.

Instructions

Create a new table in an Airtable base. Returns the generated table ID. The table starts with default fields (Name, Notes, Attachments, Status, etc.) — use list_fields after creation to inspect them.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
appIdYesThe Airtable base/application ID
nameYesName for the new table
debugNoWhen true, include raw Airtable response in output for diagnostics

Implementation Reference

  • The tool handler for create_table. Takes appId and name, calls client.createTable(), returns the new table's ID.
    async create_table({ appId, name, debug }) {
      const result = await client.createTable(appId, name);
      return ok(
        { created: true, tableId: result.tableId, name },
        result,
        debug,
      );
    },
  • The AirtableClient.createTable() method that makes the actual HTTP POST to Airtable's internal API at /v0.3/table/{newTblId}/create, generating a new table ID client-side.
    async createTable(appId, name) {
      assertAirtableId(appId, 'appId');
      const tableId = 'tbl' + this._genRandomId();
      const url = `https://airtable.com/v0.3/table/${tableId}/create`;
    
      const payload = { applicationId: appId, name };
    
      const res = await this.auth.postForm(url, this._mutationParams(payload, appId), appId);
    
      if (!res.ok) {
        const errBody = await res.text().catch(() => '');
        throw new Error(`createTable failed (${res.status}): ${errBody}`);
      }
    
      this.cache.invalidate(appId);
      const data = await res.json().catch(() => ({}));
      return { tableId, ...data };
    }
  • The tool schema/definition for create_table within the TOOLS array, specifying name, description, annotations, and inputSchema (appId, name, debug).
    {
      name: 'create_table',
      description: 'Create a new table in an Airtable base. Returns the generated table ID. The table starts with default fields (Name, Notes, Attachments, Status, etc.) — use list_fields after creation to inspect them.',
      annotations: { readOnlyHint: false, destructiveHint: false, idempotentHint: false, openWorldHint: false },
      inputSchema: {
        type: 'object',
        properties: {
          appId: { type: 'string', description: 'The Airtable base/application ID' },
          name: { type: 'string', description: 'Name for the new table' },
          debug: debugProp,
        },
        required: ['appId', 'name'],
      },
    },
  • Registration of create_table in the TOOL_CATEGORIES map, associating it with the 'table-write' category for profile-based enable/disable.
    create_table:           'table-write',
  • Mirror registration of create_table in the extension-side TOOL_CATEGORIES (mirrors the mcp-server config for the VS Code extension tool profile manager).
    create_table:              'table-write',
Behavior3/5

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

Annotations indicate readOnlyHint=false and destructiveHint=false, so the description's 'Create' is consistent as a non-destructive mutation. However, it adds no additional behavioral details beyond return value and default fields.

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?

Two succinct sentences, front-loaded with purpose. Every sentence adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description adequately explains the return (table ID) and mentions default fields. It could mention potential errors or prerequisites but is sufficient for a creation tool.

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 coverage is 100% with descriptions for all 3 parameters. The description does not add extra meaning beyond what the schema already provides.

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 action ('Create a new table') and the resource ('in an Airtable base'), with a specific outcome ('Returns the generated table ID'). It distinguishes from sibling tools like create_field or create_view.

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

Usage Guidelines3/5

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

The description implies usage context (table starts with default fields, inspect with list_fields) but does not explicitly state when to use this tool versus alternatives or when not to use it.

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/Automations-Project/VSCode-Airtable-Formula'

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