Skip to main content
Glama
Sign In

Frontman for WordPress

by io.github.frontman-ai
OverviewDiscussionsAdmin

wp_write_public_file

Destructive

Replace allowlisted public text after approval. Physical creation stops generated updates; manual removal restores generation. Saved and publicly verified are separate; never retry automatically.

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_id": "<site_id>",
      "name": "<name>",
      "content": "<content>",
      "expected_revision": "<expected_revision>",
      "confirm": "<confirm>"
    },
    "name": "wp_write_public_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
confirmYesTrue only after user approval of the diff and takeover warning.
contentYesExact replacement UTF-8 text, at most 128 KiB.
site_idYesThe connected site's id returned by list_sites. Call list_sites first; do not use a URL or WordPress post ID.
expected_revisionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description adds genuinely non-obvious behavior: creating the file physically halts generated updates, manual removal restores generation, and 'saved' is distinct from 'publicly verified'. The no-auto-retry warning is real operational guidance beyond the annotation set.

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 action and the approval gate before the side-effect caveats. No filler, though the telegraphic phrasing ('Physical creation stops generated updates') demands inference from the reader.

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, non-idempotent write with no output schema, the description covers the risk surface (approval, generation takeover, verification split, no retry) but leaves the concurrency/revision contract and post-write verification path unexplained, which matters when the tool is irreversible.

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 coverage is 60% and the description adds little parameter-level detail; it reinforces the approval gate behind confirm but never explains expected_revision (a 64-hex token implying concurrency control) or the practical difference between the three allowlisted filenames. Baseline 3 given partial schema coverage.

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?

'Replace allowlisted public text' gives a specific verb and resource, and the allowlist is concretely mirrored by the schema's enum (robots.txt, llms.txt, llms-full.txt). It is distinguishable from the wp_read_public_file sibling by the write verb, though it never names that sibling.

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?

'after approval' establishes the precondition, and 'never retry automatically' gives explicit retry guidance, which is meaningful for a destructive tool. However, there is no statement of when to prefer this over reading first, or what to do if verification fails beyond not retrying.

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

All Frontman for WordPress toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources