Skip to main content
Glama

list_tables

Read-onlyIdempotent

Lists all tables in an Airtable base, returning their names and IDs. Enables quick identification of table structure for further operations.

Instructions

List all tables in an Airtable base with their IDs and names. Uses lightweight scaffolding data.

Input Schema

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

Implementation Reference

  • The main handler function for list_tables. Calls client.getScaffoldingData(appId) to fetch lightweight table scaffolding data, extracts tables from the response, and returns a summary of table IDs and names. Uses the lightweight scaffolding API endpoint rather than the full application/read endpoint.
    async list_tables({ appId, debug }) {
      const raw = await client.getScaffoldingData(appId);
      const tables = raw?.data?.tableSchemas || raw?.data?.tables ||
        raw?.data?.tableOrder?.map(id => {
          const t = raw?.data?.tableDatas?.[id] || raw?.data?.tableById?.[id] || {};
          return { id, name: t.name || id };
        }) ||
        Object.values(raw?.data?.tableById || {});
      const summary = tables.map(t => ({
        id: t.id,
        name: t.name,
      }));
      return ok(summary, raw, debug);
    },
  • The input schema definition for list_tables. Defines the tool name, description ('List all tables...uses lightweight scaffolding data'), annotations (readOnlyHint: true), and inputSchema (requires appId, optional debug). Registered in the TOOLS array.
    {
      name: 'list_tables',
      description: 'List all tables in an Airtable base with their IDs and names. Uses lightweight scaffolding data.',
      annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true, openWorldHint: false },
      inputSchema: {
        type: 'object',
        properties: {
          appId: { type: 'string', description: 'The Airtable base/application ID' },
          debug: debugProp,
        },
        required: ['appId'],
      },
    },
  • Registration of list_tables in the TOOL_CATEGORIES mapping, categorizing it as 'read' (read-only/inspection).
    list_tables:            'read',
  • Mirror registration of list_tables in the VS Code extension's tool-profile mapping, also categorized as 'read'.
    list_tables:               'read',
  • The getScaffoldingData method on AirtableClient that the list_tables handler calls. Hits the Airtable internal API endpoint /v0.3/{appId}/getApplicationScaffoldingData for lightweight data, uses caching via SchemaCache.
    async getScaffoldingData(appId) {
      assertAirtableId(appId, 'appId');
      const cached = this.cache.getScaffolding(appId);
      if (cached) return cached;
    
      const url = `https://airtable.com/v0.3/${appId}/getApplicationScaffoldingData`;
      const res = await this.auth.get(url, appId);
      if (!res.ok) {
        const text = await res.text();
        throw new Error(`getScaffoldingData failed (${res.status}): ${text}`);
      }
      const data = await res.json();
      this.cache.setScaffolding(appId, data);
      return data;
    }
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, so the description's addition of 'Uses lightweight scaffolding data' adds minor but useful context about performance. No contradiction with annotations.

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 two sentences, front-loaded, and every word is necessary. No extraneous information.

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?

For a simple read-only list tool with good annotations, the description is nearly complete. However, it does not mention whether results are paginated or if there are any limits, which could be useful context.

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% (both parameters described in schema). The description does not add further meaning beyond the parameter descriptions already present.

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 'List all tables in an Airtable base with their IDs and names,' using a specific verb ('list') and resource ('tables'), and distinguishes from sibling tools like 'get_table_schema' or 'get_base_schema'.

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 does not provide explicit guidance on when to use this tool versus other listing or schema tools, nor does it mention any conditions or exclusions. Usage is implied but not articulated.

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