Skip to main content
Glama
backblaze-labs

Backblaze B2 MCP Server

Official

b2_update_bucket

DestructiveIdempotent

Update an existing B2 bucket's type, CORS rules, lifecycle, encryption, Object Lock, and replication settings. Apply changes without recreating the bucket.

Instructions

Update the settings of an existing B2 bucket, including type, CORS rules, lifecycle rules, encryption, and replication configuration.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
confirmNoConfirm a destructive change (making the bucket public, weakening Object Lock/lifecycle, or changing replication). Required when the server destructive policy is 'confirm' (the default); non-destructive updates do not need it.
bucketIdYesThe ID of the bucket to update.
corsRulesNoCORS rules: <=100. allowedOrigins/allowedOperations require 1-100 non-empty strings; allowedHeaders/exposeHeaders allow <=100. Strings <=999 chars. Per-rule UTF-8 total <1,000. Names unique.
bucketInfoNoCustom metadata: <=10 pairs. Keys: 1-50 UTF-8 bytes, chars A-Z a-z 0-9 . _ ` ~ ! # $ % ^ & * ' | + -, no b2- prefix. Values total <=10,000 UTF-8 bytes.
bucketTypeNo
ifRevisionIsNoConditional update — only update if the bucket revision matches this value.
lifecycleRulesNo
fileLockEnabledNoEnable Object Lock on the bucket. Unlike S3's PutObjectLockConfiguration (which only enables lock at bucket creation), the B2 native API allows enabling Object Lock on an existing bucket here. Requires the writeBucketRetentions capability.
defaultRetentionNoDefault Object Lock retention for newly uploaded objects. Requires Object Lock enabled on the bucket. Send { mode: null, period: null } to clear.
replicationConfigurationNo
defaultServerSideEncryptionNo
Install Server

TDQS

A3.5/5.0
Behavior2/5

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

Annotations already identify this as destructive and non-read-only, but the description itself adds no behavioral context beyond 'update.' It does not mention confirmation requirements, destructive consequences, or how updates apply. The confirm parameter appears only in the schema, not the tool description.

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?

A single sentence with the verb and resource front-loaded and no filler. Every phrase contributes to understanding what the tool operates on and what it can change.

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

Completeness3/5

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

For an 11-parameter tool with nested objects and no output schema, the one-line description is adequate for basic tool selection but leaves important caveats—destructive confirmation, Object Lock requirements, and update semantics—to the schema and annotations. It is not incomplete enough to block use, but it is not fully self-sufficient.

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 64%, so the schema carries most parameter documentation. The description adds a useful high-level category list, but it omits key parameters like confirm, fileLockEnabled, defaultRetention, bucketInfo, and ifRevisionIs, so it only partially compensates for the coverage gap.

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 uses a specific verb ('Update') with a clear resource ('existing B2 bucket') and lists major setting categories (type, CORS rules, lifecycle rules, encryption, replication). This clearly separates it from siblings like b2_create_bucket, b2_delete_bucket, and b2_set_bucket_notification_rules.

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

Usage Guidelines3/5

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

The phrase 'existing B2 bucket' implies an update use case, and the listed settings suggest when to choose this tool. However, there is no explicit guidance about when not to use it or which sibling to prefer for related tasks such as notification rules or lifecycle-only updates.

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

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/backblaze-labs/b2-mcp'

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