Documentation Index
Fetch the complete documentation index at: https://docs.asteragents.com/llms.txt
Use this file to discover all available pages before exploring further.
What it does
The Get Airtable Schema tool is how your agent learns what’s in your Airtable account at runtime. It has two modes:- Called without arguments — returns every base (workspace) the integration has access to, with each base’s
id,name, andpermissionLevel - Called with a
baseId— returns every table in that base with full field metadata (names, types, select choices, linked-table references) plus views
baseId, tableIdOrName, and field names needed by Search Airtable and Manage Airtable Records.
Key features
- Dynamic discovery — no need to hardcode base IDs or field names in the agent’s system prompt
- Returns select choices for
singleSelectandmultipleSelectsfields so the agent knows valid values - Returns
linkedTableIdformultipleRecordLinksfields so the agent can chase relationships - Includes view IDs + names so you can scope later queries to a specific view
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
baseId | string | No | Airtable base ID (starts with app). If omitted, returns the list of bases the PAT can reach. If provided, returns tables + fields for that base. |
Common use cases
List accessible bases
baseId you need.
Inspect a base’s tables and fields
Agent workflow pattern
- Call
airtable_get_schemawith no args → pick the right base - Call
airtable_get_schemawith thatbaseId→ learn table + field names - Call
airtable_search/airtable_manage_recordsusing the discovered IDs
What you get back
No-baseId mode:
bases[]— each withid,name,permissionLevel(none,read,comment,edit,create)count— number of basesmessage— reminder to call again with a baseId to inspect tables
baseId mode:
baseId,tableCounttables[]— each with:id,name,description,primaryFieldId,fieldCountfields[]— each withid,name,type,description, optionalchoices(for select fields), optionallinkedTableId(for record links)views[]— each withid,name,type(grid,kanban, etc.)
Best practices
- Call it early. Agents that skip discovery and guess field names will fail on any table with custom naming
- Cache the baseId. Once you’ve identified the right base, reuse its id across calls — it doesn’t change
- Prefer field IDs over names when the table might be renamed, but names work too and are easier for humans to read
- Use
permissionLevelto avoid write actions on read-only bases — the token may have list access without write access
Troubleshooting
“No bases returned”- The PAT needs the
schema.bases:readscope - The PAT must have access granted to at least one base (scopes aren’t enough — you also select specific bases during PAT creation)
- Confirm the
baseIdstarts withappand was copied from the same Airtable account as the PAT - Use the no-args mode first to list the bases the PAT can actually see
schema.bases:readis required for field metadata; if the scope was omitted, you may see base-level info but no field details
Related tools
- Search Airtable — query records in a table discovered via this tool
- Manage Airtable Records — create/update/delete records
