Skip to main content
Glama
jonradoff

LightCMS

by jonradoff
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Go
Remote

Update Content

update_content
DestructiveIdempotent

Modify existing content by ID: send only changed fields, auto-create a new version, and validate changes with a dry run before saving.

Instructions

Update an existing content item by ID. Creates a new version automatically. Only send fields you want to change.

For partial data updates, only the keys you include in "data" are changed — existing keys are preserved (merge semantics). Use clear_fields: ["field1", "field2"] to explicitly set fields to empty string. Set dry_run: true to validate the update without saving. To update by URL path instead of ID, use update_content_by_path. Always include version_comment so the version history is useful.

Up to 20 concurrent update_content calls are safe. For larger batches (>20 items), prefer bulk_update_content instead.

Example: {"id": "abc123", "data": {"body": "Updated text"}, "version_comment": "Revised intro paragraph"}

Content data fields support rich markup features:

  • [[Wikilinks]] and [[Page Title|display text]] — link to other pages by title or path; auto-update when paths change

  • [[include:snippet-name]] — embed a named snippet inline (reusable callouts, CTAs, disclaimers)

  • #hashtags — mention #tagname anywhere to automatically tag the page

  • Markdown fields (type "markdown") — GitHub Flavored Markdown converted to HTML at publish time Templates can use {{.lc_toc}} in their HTML layout to inject an auto-generated table of contents.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesContent ID (MongoDB ObjectID),required
dataNoTemplate field values
holdNotrue puts the page on hold so it cannot be published; false clears the hold. Holding a published page does not unpublish it
slugNoURL slug
tagsNoTags for lc:query index pages
titleNoContent title
dry_runNoIf true, validate the update without saving
noindexNotrue hides the page from search engines and AI; false makes it visible again
categoryNoContent category
og_imageNoOpen Graph image URL
raw_modeNoUse raw HTML mode
use_themeNoApply site theme/layout
author_urlNoAuthor profile URL; empty string clears it
use_footerNoInclude site footer
use_headerNoInclude site header
author_nameNoAuthor name for structured data and feeds; empty string reverts to the site default
folder_pathNoFolder path
template_idNoTemplate ID (MongoDB ObjectID)
clear_fieldsNoField names to clear to empty string (removes ambiguity about how to delete field content)
set_raw_modeNoSet to true to explicitly update raw_mode (needed to set it to false)
set_use_themeNoSet to true to explicitly update use_theme (needed to set it to false)
set_use_footerNoSet to true to explicitly update use_footer (needed to set it to false)
set_use_headerNoSet to true to explicitly update use_header (needed to set it to false)
version_commentNoOptional comment describing this version change
meta_descriptionNoSEO meta description

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv7.3.4
    • addedInput schema / properties / author_name
      Added value: +{
+  "description": "Author name for structured data and feeds; empty string reverts to the site default",
+  "type": [
+    "null",
+    "string"
+  ]
+}
    • addedInput schema / properties / author_url
      Added value: +{
+  "description": "Author profile URL; empty string clears it",
+  "type": [
+    "null",
+    "string"
+  ]
+}
    • addedInput schema / properties / hold
      Added value: +{
+  "description": "true puts the page on hold so it cannot be published; false clears the hold. Holding a published page does not unpublish it",
+  "type": [
+    "null",
+    "boolean"
+  ]
+}
    • addedInput schema / properties / noindex
      Added value: +{
+  "description": "true hides the page from search engines and AI; false makes it visible again",
+  "type": [
+    "null",
+    "boolean"
+  ]
+}
  2. First observedv4.2.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations declare idempotentHint=true and destructiveHint=true, but the description adds the context those hints cannot convey: automatic version creation, merge semantics (unlisted keys preserved), clear_fields for explicit deletion, and dry_run validation. It also discloses a concurrency safety ceiling, which is genuinely new operational information.

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?

Well front-loaded — purpose, merge semantics, clear_fields, dry_run, and routing all appear before the lengthy markup reference block. The markup and {{.lc_toc}} template section is the weakest part: it is closer to reference material and is somewhat tangential to selecting or calling this specific tool, making the description longer than strictly required.

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 25-parameter mutation tool with no output schema, the description covers the non-obvious surfaces (merge vs clear, dry-run, versioning, batch routing, concurrency). It is slightly short on failure/conflict behavior — e.g. whether a version conflict or an existing content lock (acquire_content_lock exists as a sibling) affects the update — which is the main remaining gap.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description goes beyond the schema on the semantically hardest parameter: it explains merge behavior for 'data', the clear_fields escape hatch, and the rich markup grammar ([[Wikilinks]], [[include:...]], #hashtags, markdown) accepted inside data fields. This is real added meaning rather than restated schema text.

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?

States a specific verb+resource ('Update an existing content item by ID') plus the key side effect ('Creates a new version automatically'), and explicitly names the siblings it is not — update_content_by_path and bulk_update_content. An agent can distinguish it from the other ~100 tools without opening a schema.

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?

Gives explicit routing rules: use update_content_by_path for URL-path targeting, bulk_update_content for batches >20, and states that up to 20 concurrent calls are safe. It also tells the caller to only send changed fields and to include version_comment. This is when-to-use and when-to-use-something-else guidance, not inference.

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

Deploy Server

Other Tools