Skip to main content
Glama

thincms_snapshot

Capture a site resource's state before test writes to restore it byte-for-byte later. Guarantees recovery to exact pre-test state regardless of the write outcome.

Instructions

Capture the current state of a site resource so it can be restored byte-for-byte later. Use BEFORE any test write against a customer site — restore returns the resource to the exact pre-test state regardless of what the test write does (null, substitute, partial update, etc.). Snapshots live in MCP wrapper memory for 24 hours; they survive across tool calls within a session but are lost on host restart. Supports scope='settings', 'template', 'page' (requires resourceId), 'post' (requires resourceId), and 'review' (requires resourceId).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
scopeYesWhat to snapshot. 'settings' captures editable site settings (excludes admin-only fields like name/domain that PUT can't restore from an editor key); 'template' captures stylesheet/pageFrame/customHeadHtml; 'page' / 'post' / 'review' capture editable fields of a single resource and require a resourceId.
siteIdNoOverride the active site for this snapshot (matches the per-call siteId pattern used by other tools). Must match a siteId from your THINCMS_SITES config.
resourceIdNoRequired for scope='page', 'post', or 'review'. The resource ID to snapshot.
Behavior4/5

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

No annotations are provided, so the description carries the full burden. It describes that snapshots live in MCP wrapper memory for 24 hours, survive across tool calls, and are lost on host restart. It also specifies what each scope captures (e.g., settings excludes admin-only fields). It does not cover failure behavior or duplication, but the disclosed traits are substantial.

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 concise (three sentences) and front-loaded with the primary purpose and usage advice. It then efficiently covers scope details and lifetime. Every sentence adds value without redundancy.

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?

Given no output schema, the description could mention the return value (e.g., snapshot identifier or handle). However, for a snapshot tool, it covers the essential behavioral aspects (scope, lifetime, usage) and the input schema is fully described. Minor gap on return value prevents a 5.

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?

Schema coverage is 100%, but the description adds significant value: for scope 'settings' it clarifies that admin-only fields are excluded; for 'page/post/review' it notes editable fields and resourceId requirement. This goes beyond the schema enum descriptions to explain behavior and constraints.

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 it captures the current state of a site resource for byte-for-byte restoration. It distinguishes from siblings like thincms_restore_snapshot by explaining the use case for pre-test writes. The verb 'capture' and resource 'site resource' are specific, and the description differentiates from other snapshot-related tools.

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?

The description explicitly says 'Use BEFORE any test write against a customer site' and explains that restore returns exact pre-test state. It also details when resourceId is required for specific scopes. While it doesn't list when not to use, the guidance is clear and actionable for the intended use case.

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/pmccarroll-fuel/thincms-mcp'

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