Skip to main content
Glama

download_formula_field

DestructiveIdempotent

Download a formula field's text to a readable .formula file with metadata header, resolving field refs to real names so it can be uploaded back unchanged. Omit outputPath to just return the formula.

Instructions

Download the formula text of a formula field to a local file. Field refs are resolved to real field names ({Field Name}, Airtable's native syntax) so the file is readable and can be uploaded back unchanged. Writes a .formula file with a # AT: metadata header (appId, tableId, fieldId, fieldName) so the file can later be uploaded back with update_formula_field or the VS Code right-click command. When outputPath is omitted, returns the formula text without writing a file.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "appId": "<appId>",
      "fieldId": "<fieldId>"
    },
    "name": "download_formula_field"
  }
}

Input Schema

NameRequiredDescriptionDefault
appIdYesThe Airtable base/application ID
debugNoWhen true, include raw Airtable response in output for diagnostics
fieldIdYesThe formula field ID (e.g. "fldXXX")
outputPathNoLocal file path to write the .formula file. When omitted, returns formula text in the response without writing a file.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.6

TDQS

A4.2/5.0
Behavior4/5

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

Annotations declare destructiveHint=true, readOnlyHint=false and idempotentHint=true; the description explains the read-and-write-to-disk nature, field-ref resolution and the metadata header, which is substantive context. It does not warn that an existing file at outputPath may be overwritten, which is the main thing the destructive hint implies.

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?

Three sentences, all load-bearing: primary action first, then file format guarantees, then the no-file fallback. No filler or repetition of schema details beyond the necessary fallback clause.

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 two-required-param export tool with no output schema, it covers the return value, file structure and downstream reuse. Only the overwrite behavior and failure modes for an invalid outputPath are left unstated.

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%, so all four parameters are already documented, including the outputPath fallback behavior which the description largely restates. The description adds only indirect meaning about what lands in the file, not parameter-level semantics.

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?

States a specific verb and resource ('Download the formula text of a formula field') plus the artifact produced (a .formula file). The singular field scope implicitly separates it from the sibling download_base_formulas, and the round-trip mention of update_formula_field anchors its role.

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?

Gives a clear conditional: omit outputPath to get the text back without writing a file, and points to update_formula_field / the VS Code command as the upload counterpart. It stops short of explicitly contrasting with download_base_formulas for base-wide extraction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.