Skip to main content
Glama

sitekick_workspace_write

DestructiveIdempotent

Plan, update, generate, validate, preview, review, apply, roll back, cancel or retry native WordPress changes in the selected isolated site. Start with plan, request and kind; omitted appearance_mode preserves customizations. Load selected existing source with source_paths, then scope overwrites/deletes through explicit_changes. New standalone themes/plugins need an explicit activation selection. MU plugin changes require exact explicit_changes paths because they load when applied. Later actions require project_id and expected_revision. Before generate, review estimated_credits/estimated_requests and pass estimate_hash as reviewed_estimate_hash. Review binds exact files and activation; follow its WordPress owner-session continuation for human approval. Tool confirmation cannot issue approval. Retain the exact original command/key after uncertain replies.

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": {
      "payload": "<payload>",
      "site_ref": "<site_ref>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "sitekick_workspace_write"
  }
}

Input Schema

NameRequiredDescriptionDefault
payloadYes
site_refYes
idempotency_keyYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

The annotations already declare destructive, non-read-only, open-world, and idempotent behavior, but the description adds critical operational context beyond them: tool confirmation cannot issue approval, review binds exact files and activation, MU plugin changes load when applied, and callers must retain the exact original command/key after uncertain replies. These details materially affect safe invocation and are not present in the structured annotations.

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?

The action list is front-loaded and nearly every clause carries a real constraint, prerequisite, or safety warning, so there is little filler. The prose is very dense and semicolon-packed, though, making it harder to scan than a more structured action-by-action breakdown would be.

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 complex, destructive, multi-stage workflow tool with nested payloads and an output schema, the description covers the important context an agent needs: workflow order, human approval boundaries, estimate review, idempotency handling, MU plugin constraints, and activation requirements. Return values need not be described because an output schema exists.

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 description coverage is 0%, so the description must carry parameter meaning, and it does substantial work by explaining action, kind, request, appearance_mode, source_paths, explicit_changes, activation, project_id, expected_revision, reviewed_estimate_hash, and idempotency retention. However, it does not explain the files object or review_hash, and it only indirectly maps site_ref and idempotency_key to their top-level fields. The compensation is strong but not complete.

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?

The description opens with a precise verb set and resource: plan, update, generate, validate, preview, review, apply, roll back, cancel, or retry native WordPress changes in a selected isolated site. The write-oriented scope clearly distinguishes it from the read sibling, and the action list tells an agent exactly what class of operation this tool performs.

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?

It gives explicit sequencing and prerequisites: start with plan, request, and kind; use source_paths to load existing source; scope overwrites/deletes through explicit_changes; require activation for standalone themes/plugins; require exact explicit_changes paths for MU plugins; later actions need project_id and expected_revision. It also explains the estimate review step and the human approval continuation path. These are concrete when-to-use and how-to-use instructions for each stage.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources