DocsMint

create_snapshot

Save a named snapshot of an existing document before a planned change so you can restore it later.

Instructions

Save a named snapshot of an existing document before a planned change. The snapshot can later be restored with restore_document_version.

Input Schema

Name	Required	Description
`label`	Yes	Snapshot label, from 1 to 200 characters.
`documentId`	Yes	UUID returned by the corresponding list or read operation.
`description`	No	Optional snapshot note, at most 1000 characters.
`workspaceId`	No	Workspace UUID from list_workspace_structure(kind=workspaces). Required for ambiguous creates and structure changes; omit to search all granted scopes.

Output Schema

Name	Required	Description	Default
`id`	Yes
`label`	No
`content`	Yes
`createdAt`	Yes
`createdBy`	Yes
`documentId`	Yes
`isSnapshot`	No
`contentJson`	No
`description`	No
`restoredFrom`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedv2.0.4Oct 27, 2026

addedInput schema / properties / workspaceId

Added value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "description": "Workspace UUID from list_workspace_structure(kind=workspaces). Required for ambiguous creates and structure changes; omit to search all granted scopes.",
+  "format": "uuid",
+  "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
+  "type": "string"
+}

removedOutput schema / properties / description / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / description / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / label / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / label / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / restoredFrom / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / restoredFrom / type
```
Added value: +[
+  "string",
+  "null"
+]
```

Changed4 schema fields changedv0.1.2Sep 28, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

changedInput schema / properties / description / description

Previous value: -"Optional snapshot note up to 1,000 characters; omit if not needed."New value: +"Optional snapshot note, at most 1000 characters."

changedInput schema / properties / documentId / description

Previous value: -"UUID of the existing document, obtained from search_documents or list_documents and visible in the active scope."New value: +"UUID returned by the corresponding list or read operation."

changedInput schema / properties / label / description

Previous value: -"Non-empty snapshot label up to 200 characters, for example 'v1.0-release'."New value: +"Snapshot label, from 1 to 200 characters."

First observedSep 27, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already declare destructiveHint=false, idempotentHint=false and openWorldHint=false, and the description's 'can later be restored' reinforces that the operation is safe and reversible. However, it does not disclose what the agent would most want beyond the annotations: whether calling twice with the same label creates duplicates, whether existing snapshots are affected, or whether any permission/grant is needed.

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?

Two sentences, both front-loaded with the action and then the recovery path. No redundant restatement of the name or title, and nothing that could be trimmed.

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 non-destructive write with full schema coverage and an output schema, the description covers the essentials: what is created and how it is undone. The remaining gap is duplicate-label behavior and permission expectations, which are minor given the annotation safety profile.

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 every parameter (label, documentId, description, workspaceId) is already documented in the schema, including the ambiguity rule for workspaceId. The description adds nothing parameter-specific beyond the word 'named,' which implicitly maps to label — baseline 3.

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: 'Save a named snapshot of an existing document.' The label/document semantics and the pre-change timing make the operation immediately understandable. It also names restore_document_version as the counterpart, though it does not distinguish itself from save_document, the nearest sibling that also writes document state.

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

Usage Guidelines4/5

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

Gives a clear usage condition — 'before a planned change' — and points to restore_document_version as the way to undo. It stops short of explicit exclusions (e.g., when to use save_document or a version restore instead), so the agent must infer the boundary.

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