Skip to main content
Glama
Sign In
MCP Hub

MCP Hub

by airano-ir
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

WordPress: Regenerate thumbnails

wordpress_regenerate_thumbnails
Destructive

Rebuild WordPress attachment thumbnails and registered image sub-sizes after format conversion, theme changes, or missing legacy sizes; target specific attachments or process batches.

Instructions

[UNIFIED] Rebuild attachment sub-sizes (the registered WP image sizes plus any from add_image_size() in the active theme). Use this after upload_media_from_url / _from_base64 with convert_to=webp|avif, after a theme switch that adds new sizes, or for legacy attachments missing thumbnails. Routes through the airano-mcp-bridge companion plugin v2.8.0+. Body shapes: either an 'ids' list to target specific attachments (max 50 per call); or all=true with offset/limit for paged batch. Returns has_more + next_offset in batch mode so callers can continue.

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": {
      "site": "<site>"
    },
    "name": "wordpress_regenerate_thumbnails"
  }
}

Input Schema

NameRequiredDescriptionDefault
allNo
idsNo
siteYes
limitNo
offsetNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.13.1

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare readOnly=false, destructive=true, idempotent=false, and the description adds real context beyond them: the airano-mcp-bridge companion plugin v2.8.0+ dependency, the max-50-per-call cap, and has_more/next_offset pagination for batch mode. However, it never explains what 'destructive' means here — whether existing sub-size files are overwritten or deleted, whether failures are partial, or what happens to attachments already up to date — leaving the annotation's most consequential hint unexplained.

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?

Front-loads purpose, then use cases, then transport/body mechanics — a sensible ordering with little waste. The '[UNIFIED]' tag and embedded plugin version are slightly noisy but do encode a real precondition, so the density is mostly earned.

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 5-parameter mutation tool with no output schema, the description covers invocation modes, pagination, batch limits, and the plugin dependency, which is close to what an agent needs. Remaining holes are the unexplained `site` parameter and the absence of any note on what regeneration does to existing files under destructiveHint=true.

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 0%, so the description carries the full burden. It usefully explains the two body shapes — 'ids' for targeted attachments (max 50) and all=true with offset/limit for paging — but leaves gaps: the `site` parameter is never mentioned, and `ids` is typed as a string in the schema while the description calls it a 'list', without clarifying the expected string encoding (comma-separated? JSON?).

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: 'Rebuild attachment sub-sizes' for registered WP image sizes plus theme-registered sizes. It clearly distinguishes its role from upload tools (it runs after upload_media_from_url/_from_base64 with convert_to=webp|avif) and from theme/attachment maintenance tasks, so an agent can identify it without opening the 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 three concrete triggers: after an upload with convert_to=webp|avif, after a theme switch that adds sizes, and for legacy attachments missing thumbnails. It also states the calling modes (specific ids vs all=true paged batch), which routes the agent between the two invocation patterns without 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