Skip to main content
Glama

airtable_manage_records

Retrieve, update, or delete single or multiple Airtable records by ID. Perform targeted lifecycle operations—get, PATCH field updates, or permanent deletion—without affecting unrelated records.

Instructions

Performs lifecycle operations on individual or batch records in Airtable: get record by ID, update fields (PATCH), delete single record, or batch delete up to multiple records.

When to Use

  • When updating specific fields on an existing record (e.g. changing Stage from 'Review' to 'Approved').

  • When retrieving the full payload of a single record by known record ID (starts with 'rec').

  • When permanently deleting one or more records by their record IDs.

When NOT to Use

  • Do NOT use this tool to insert dozens of new rows. Use 'airtable_batch_upsert' instead.

  • Do NOT use this tool for formula-based search or multi-record filtering. Use 'airtable_query_records' instead.

  • Do NOT use this tool to delete an entire table or change schema definitions. Use 'airtable_modify_schema' instead.

Operational Disclosures

  • Destructive Behavior: The 'delete' and 'batch_delete' actions permanently remove records from Airtable (moved to base trash for 7 days).

  • Partial Updates: The 'update' action performs a PATCH: only specified fields are modified; unmentioned fields retain their existing values.

  • Rate Limits: Single requests execute in 1 call; 'batch_delete' automatically chunks IDs by 10 and respects the 5 req/sec rate limit.

  • Auth Scopes: Requires Personal Access Token with 'data.records:write' (or 'data.records:read' for 'get').

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesAction to perform: 'get' retrieves a record, 'update' modifies fields (PATCH), 'delete' removes one record, 'batch_delete' removes an array of records
fieldsNoField key-value pairs to update (required when action is 'update'), e.g. {"Stage": "Approved", "Reviewer Notes": "Verified"}
base_idYesAirtable Base ID (starts with app, e.g. appoorUuG6wgx8dJ1)
typecastNoWhen true, automatically creates new select choices or casts strings to linked records (default: true)
record_idNoTarget Record ID starting with 'rec' (required for 'get', 'update', and single 'delete')
record_idsNoArray of Record IDs starting with 'rec' (required when action is 'batch_delete')
table_name_or_idYesTarget Table Name or Table ID

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.1.1

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and delivers: it discloses destructive behavior (permanent removal with 7-day trash), PATCH partial-update semantics, rate-limit handling (batch_delete chunks by 10), and required auth scopes. This is comprehensive behavioral disclosure for a mutating tool.

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 organized into clear labeled sections ('When to Use', 'When NOT to Use', 'Operational Disclosures'), front-loads the core purpose in the first sentence, and contains no filler. Every section earns its place by conveying actionable selection or invocation 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 7-parameter, 4-action tool with no output schema and no annotations, the description covers usage context, exclusions, destructive behavior, rate limits, and auth. It does not describe response payloads or error behavior, but those are less critical for correct invocation; the guidance is otherwise complete enough for an agent to call the tool safely and accurately.

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 the schema already documents all seven parameters, their formats, and action-specific requirements. The tool description adds only marginal parameter insight (e.g., PATCH semantics affecting how 'fields' is interpreted), but does not significantly surpass the schema's own parameter docs, so the baseline 3 is appropriate.

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 opening sentence names a specific verb ('performs lifecycle operations') and resource ('records in Airtable') and enumerates the four concrete actions: get, update (PATCH), delete, and batch delete. It immediately distinguishes this tool from siblings like airtable_batch_upsert and airtable_query_records by limiting scope to lifecycle operations on known record IDs.

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?

The 'When to Use' section gives concrete scenarios (updating a field, retrieving by known ID, deleting records) and the 'When NOT to Use' section explicitly names three sibling alternatives: airtable_batch_upsert, airtable_query_records, and airtable_modify_schema. This tells an agent exactly when to select this tool versus its siblings with no inference required.

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