Skip to main content
Glama
domdomegg

airtable-mcp-server

Upload Attachment

upload_attachment

Upload a file (up to 5 MB) as base64 to an existing Airtable record's attachment field; for larger files, use a public URL.

Instructions

Upload a file directly to an attachment field on an existing record using Airtable's upload API. Supports files up to 5 MB. For larger files, use create_record or update_records with a public URL. The record must already exist.

Input Schema

NameRequiredDescriptionDefault
fileYesRaw base64-encoded file content (no data URL prefix)
baseIdYesThe ID of the base
filenameYesFilename for the attachment (e.g. "image.jpg")
recordIdYesThe ID of the existing record (e.g. recXXXXXXXXXXXXXX)
contentTypeYesMIME type of the file (e.g. "image/jpeg", "image/png", "application/pdf")
attachmentFieldIdOrNameYesThe ID or name of the attachment field (e.g. fldXXXXXXXXXXXXXX or "Images")

Output Schema

NameRequiredDescriptionDefault
idYes
fieldsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.14.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare the safety profile (readOnlyHint=false, destructiveHint=false), so the description's size cap and existence prerequisite add real behavioral value. It does not say whether an upload appends to or replaces the existing attachments in the field, nor whether the call is synchronous — the main remaining behavioral gap.

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 tight sentences: capability first, limit and escape hatch second, prerequisite last. No filler, no restatement of the tool name or title, and the most important constraint is front-loaded.

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?

An output schema exists, so return values need no explanation, and the description covers the size limit, the alternative path, and the record prerequisite. The one thing an agent would still want — whether the upload overwrites or adds to existing field attachments — is absent.

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%, so each of the six parameters (base64 file, filename, contentType, baseId, recordId, field identifier) is already documented at the field level. The description adds only cross-cutting facts (5 MB cap, record must exist) rather than per-parameter semantics, so the baseline 3 applies.

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?

Specific verb (upload), resource (file), and destination (an attachment field on an existing record), plus the underlying mechanism (Airtable's upload API). It is clearly distinguishable from create_record/update_records, which are named only as the large-file alternative.

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

Usage Guidelines5/5

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

Gives an explicit constraint (files up to 5 MB), an explicit when-not with the alternative to use instead ('For larger files, use create_record or update_records with a public URL'), and a prerequisite ('The record must already exist'). Nothing about routing is left to inference.

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