Skip to main content
Glama
Sign In
Nucleo for WordPress

Nucleo for WordPress

by nucleowp
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Hybrid

nucleo-content-upsert

Destructive

Create or update WordPress content by type and slug, trash selected items, and validate changes with a dry run before writing anything.

Instructions

Creates or updates content items by type and slug, and trashes items with status "trash". An item identical to the saved one is not written and reports action "unchanged" (counted in unchanged). An item with errors writes nothing; the others go on. With "dryRun" nothing is written.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "items": "<items>"
    },
    "name": "nucleo-content-upsert"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemsYesItems to create or update. Partial: a key left out keeps its value.
mediaNoMap from file name to URL, from the manifest.
dryRunNoCheck the items and report the planned actions, without writing. Default false.
pendingNoSymbolic references that the push will create. Only with dryRun.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description goes beyond them by disclosing partial-failure semantics (one bad item writes nothing but the others proceed), no-op behavior for identical items reported as 'unchanged', and that dryRun performs no writes. It stops short of describing required permissions or the shape of per-item error results, and the 'identical item is not written' behavior sits in mild tension with idempotentHint=false, though it is not a direct contradiction.

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?

Four short sentences, front-loaded with the create/update/trash scope, then the no-op, error-isolation, and dryRun rules in a logical order. The dryRun sentence is somewhat redundant with the schema text, but nothing is verbose or padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, batch-capable mutation tool with no output schema, the description omits the return shape beyond the hint of an 'unchanged' counter and per-item error reporting. The agent knows what the tool does and how failures behave, but not what it gets back or how many result records to expect.

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 the schema already documents items, media, dryRun, and pending in detail. The description adds a little operational meaning to dryRun and to status 'trash', but largely paraphrases what the schema fields already say, matching the baseline 3 for high-coverage schemas.

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?

The description names a specific verb set (create/update/trash) and the resource (content items keyed by type and slug), which is far more than a restatement of the name. It doesn't explicitly contrast itself with content-get or content-list, so the agent must infer that boundary from the tool name, keeping this at a 4.

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?

Usage context is implied rather than stated: the mention that 'with dryRun nothing is written' signals a preview mode, and the error-isolation rule hints at bulk push usage. There is no explicit when-to-use vs alternatives guidance (e.g., when to reach for this over a single-item path) and no prerequisites or permission notes.

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