Skip to main content
Glama

update_content

Idempotent

Save the working draft of a content item: merge field updates by default, or pass merge:false with a revision to replace the map and avoid overwriting concurrent edits.

Instructions

Save the working draft of a content item. data maps field name → value. For LONG text/markdown values prefer set_field: a flat string parameter survives tool-call serialization that can mangle long strings nested inside data. IMPORTANT: each field's value shape depends on its content-type field TYPE — call get_content_type first. text/markdown → a plain string; richtext → a TipTap doc object {type:'doc',content:[…]}; contentArea → an ARRAY of block instances; reference → {documentId,type?}; select → one option-value string; image → an asset id. By default data is MERGED over the current draft — fields you omit are kept. Pass merge:false to REPLACE the whole map (then you must send every required field, or the next publish will fail validation). With merge:false, also pass the revision you got from get_content: the write is then refused (409) if a human editor changed the draft meanwhile, instead of overwriting them. Merged writes don't need it — they read current data at write time.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataYesField name → value, shaped per get_content_type's valueFormat. Pass {} to change only name/slug/displayInNav.
nameNoNew display name. Omit to keep it.
siteNoSite slug or id to act in (multisite). Omit to use this server's default site. Call list_sites to see what exists — an empty tree or search usually means the wrong site, not missing content.
slugNoNew URL slug for a page; publishing it adds a 301 from the old URL automatically. Omit to keep it.
mergeNoDefault true: shallow-merge data over the current draft. false = replace the whole field map
localeNoLocale code. Omit for the document's own locale (its site-default variant, else its only variant).
revisionNoOptimistic concurrency: the `revision` from get_content. If a human (or another agent) has changed the draft since, the write is refused instead of overwriting their work. Recommended whenever merge:false
documentIdYesThe item's documentId (stable across locales and versions), e.g. from tree, list_pages or get_content.
displayInNavNoWhether the page appears in the site navigation. Omit to keep it.
allowLanguageMismatchNoSet true ONLY to deliberately write text whose language differs from the locale branch (the guard otherwise refuses, so e.g. Norwegian text can't silently land on the 'en' branch)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.1.3
    • addedInput schema / properties / data / description
      Added value: +"Field name → value, shaped per get_content_type's valueFormat. Pass {} to change only name/slug/displayInNav."
    • addedInput schema / properties / displayInNav / description
      Added value: +"Whether the page appears in the site navigation. Omit to keep it."
    • changedInput schema / properties / documentId / description
      Previous value: -"Content documentId"New value: +"The item's documentId (stable across locales and versions), e.g. from tree, list_pages or get_content."
    • addedInput schema / properties / name / description
      Added value: +"New display name. Omit to keep it."
    • addedInput schema / properties / slug / description
      Added value: +"New URL slug for a page; publishing it adds a 301 from the old URL automatically. Omit to keep it."
  2. First observedv0.1.0

TDQS

A4.7/5.0
Behavior4/5

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

Goes well beyond the annotations: default merge behavior (omitted fields kept), the 409 refusal when a human editor changed the draft, and the validation failure that follows an incomplete merge:false replace. The one thing not addressed is that merge:false can silently drop fields the caller didn't resend, which sits slightly in tension with destructiveHint=false, though the refusal path mitigates it.

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?

Purpose is front-loaded in the first sentence and the body is dense with load-bearing detail, but the run-on paragraph mixing value-shape rules, merge semantics, and concurrency would scan faster as short labeled segments. Nearly every sentence earns its place, so the length is defensible rather than padded.

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?

For a 10-parameter mutation with nested objects and no output schema, the description covers the write semantics (merge vs replace), the concurrency contract, the type-dependent value shapes, and the fallback to set_field. Nothing an agent needs before invoking it correctly is missing.

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 already 100%, yet the description adds the highest-value information: the per-content-type value shapes (richtext TipTap doc, contentArea block-instance array, reference {documentId,type?}, select option string, image asset id) that the schema's generic `additionalProperties: {}` cannot express. It also explains merge/revision interplay rather than restating field descriptions.

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?

Opens with a specific verb+resource ("Save the working draft of a content item") and immediately distinguishes itself from siblings by naming set_field as the preferred path for long values and get_content_type as a prerequisite. An agent can tell what this tool does and how it differs from create_content/set_field/publish without opening any 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?

Explicit when-to-use routing: prefer set_field for long text/markdown because a flat string parameter survives serialization; call get_content_type first for value shapes; use merge:false with a revision from get_content for replace semantics, and merged writes don't need it. This is close to a decision tree, not just context.

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