2b2t Atlas

find_preserved_builds

Read-only

Find preserved 2b2t builds that have both a public map render and a downloadable bounded world snapshot, optionally filtered by group, dimension, or capture dates. Prefer interactiveUrl for human links and citations. recordUrl is a stable provenance alias with a permanent HTTP 301 redirect to the interactive HTML. Use apiUrl or JSONL for JSON. Derivatives use locationInteractiveUrl/locationRecordUrl.

Input Schema

Name	Required	Description
`group`	No	Optional builder or owning group name.
`limit`	No	Maximum results, from 1 to 100. Defaults to 20.
`query`	No	Optional location or history search text.
`to_date`	No	Optional inclusive latest capture date in YYYY-MM-DD form.
`dimension`	No	Optional Minecraft dimension: 0 Overworld, 1 Nether, or 2 End.
`from_date`	No	Optional inclusive earliest capture date in YYYY-MM-DD form.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 25, 2026
- changedOutput schema / properties / result / items / properties / y / type
```
Previous value: -"integer"New value: +[
+  "integer",
+  "null"
+]
```
Changed1 schema field changedSep 28, 2026
- addedOutput schema / properties / result / items / properties / recordUrl
```
Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
```
First observedSep 14, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description's real contribution is output semantics: recordUrl is a stable alias with a permanent 301 to the interactive HTML, apiUrl/JSONL serve JSON, and derivatives use location-prefixed fields. That is genuinely useful behavioral context an agent cannot get from annotations. Missing only operational details like pagination or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core definition and its render+snapshot constraint are front-loaded in the first sentence; the remaining sentences are dense field-selection guidance with little waste. It runs slightly long for a listing tool, but each URL sentence carries distinct information.

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?

With an output schema present, the description does not need to enumerate return values, and it instead covers the two things the schema cannot: the inclusion invariant (render AND snapshot) and which URL field to use for human citations versus JSON consumers. An agent can call this correctly from the description plus schema alone.

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 six parameters including formats (YYYY-MM-DD dates, dimension 0/1/2) are already documented in the schema. The description restates the filter categories without adding syntax or edge-case meaning, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Find preserved 2b2t builds') and adds a distinguishing scope constraint: results must have both a public map render and a downloadable bounded world snapshot. That is more specific than any sibling name suggests, though it never explicitly contrasts with get_group_builds or search_world_find, so an agent must infer the boundary.

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 'optionally filtered by group, dimension, or capture dates' clause implies when the filters apply, and the URL guidance tells the agent which field to pick for which purpose. But there is no explicit when-to-use-this-vs-sibling statement and no note about when the render+snapshot invariant would exclude otherwise relevant results.

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

All 2b2t Atlas tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.