Skip to main content
Glama
trustxai
by trustxai

airbyte_trigger_refresh

Destructive

Trigger a refresh of Airbyte streams to re-read source data and merge or truncate destination records, ensuring no downtime. For self-managed Airbyte only.

Instructions

Trigger a refresh for one or more streams in a connection.

Uses the internal Configuration API to start a refresh job. Unlike a reset (which drops destination data first), a refresh re-reads from source and swaps/merges data only on success — no downtime.

Requires a self-managed Airbyte deployment where the Configuration API (/api/v1) is accessible. NOT available on Airbyte Cloud.

When to Use: - A stream has data gaps from a connector bug and you want to re-read without clearing the destination table first. - You need to reconcile stale rows in an incremental-append stream without risking downtime from a full reset. - Source data was corrected and you want to pull a fresh copy while the old data remains queryable.

When NOT to Use: - On Airbyte Cloud (internal API not available). - If a full reset is acceptable, use airbyte_trigger_sync with job_type='reset' instead (simpler, public API). - If the connection is already running a job, wait for it to finish first.

Refresh Types: - 'merge' (default): Retain previous records and merge new data. Old and new generations coexist, distinguished by _airbyte_generation_id. Safest option. - 'truncate': Replace destination data with the fresh read. Only newly synced rows appear after completion.

Returns: The created job with its jobId and initial status.

Examples: Refresh a single stream (merge): params = { "connection_id": "a1b2c3d4-...", "streams": [{"name": "oe-trailer"}] } Refresh multiple streams (truncate): params = { "connection_id": "a1b2c3d4-...", "streams": [ {"name": "oe-trailer"}, {"name": "arinvitm", "namespace": "public"} ], "refresh_type": "truncate" }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paramsYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

Discloses that it requires a self-managed Airbyte deployment, explains the refresh process (re-reads, swaps/merges on success, no downtime), and mentions waiting for running jobs. These details go beyond the annotations' destructiveHint and readOnlyHint.

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?

Well-organized with clear headings for usage, refresh types, return value, and examples. Every sentence adds value, and the core purpose is stated upfront.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all necessary context: tool purpose, prerequisites (self-managed), usage scenarios, refresh type options, and return format. The presence of an output schema further completes the picture.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds meaning beyond the input schema by explaining refresh types ('merge' vs 'truncate') with behavioral differences and providing concrete examples for single and multiple streams, plus enumeration of valid values.

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 the tool triggers a refresh for streams in a connection, distinguishing it from siblings like airbyte_trigger_sync (reset) and noting it uses the internal Configuration API, not available on Cloud.

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?

Explicitly lists when to use (data gaps, reconcile stale rows, corrected source) and when not to use (on Airbyte Cloud, if reset is acceptable, if connection is busy), with a suggested alternative (airbyte_trigger_sync with reset).

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/trustxai/airbyte-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server