Skip to main content
Glama

sitekick_workspace_read

Read-onlyIdempotent

Inspect native WordPress source as paged inventory metadata (offset/limit), or fetch only selected file bytes with paths. Use get/status to continue a saved workspace project. Open review_url in the owner browser workspace to access private previews; preview_url requires its owner gateway session. Export returns a standard ZIP archive of its retained scoped files; one theme/plugin package has the normal slug root. Existing customizations are preserved by default. Generation and effects are explicit workspace.write actions.

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>"
    },
    "name": "sitekick_workspace_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
payloadYes
site_refYes

Output Schema

NameRequiredDescriptionDefault

No arguments

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 establish readOnly, idempotent, non-destructive, open-world behavior, so the description's job is added context, and it delivers: export yields a standard ZIP with a normal slug root for single packages, preview_url demands an owner gateway session, and review_url is opened in the owner browser workspace for private previews. The "customizations are preserved by default" clause is tangential and slightly ambiguous for a read tool, but it is framed as a distinction from write actions rather than a claim of mutation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The primary inventory/file-fetch behavior is front-loaded, which is good, but the description is a dense run-on that bundles access-URL semantics, ZIP structure, customization preservation, and write-tool disambiguation into one paragraph. The customization sentence does little work for a read tool and could be dropped or separated.

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 nested payload with an action enum plus a site_ref identifier and an output schema covering returns, the description does enough to call the tool: it explains each action's effect and the two access URLs. The visible gap is per-action parameter applicability and the undocumented project_id, which matters for the status path.

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 must carry parameter meaning, and it partially does: it ties offset/limit to paged inventory and paths to byte fetching. It never mentions project_id, never states which parameters apply to which action (e.g. paths only meaningful for get, limit/offset only for inspect), and does not surface the 200-item caps.

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 concrete verbs and resources per action: paged inventory metadata for inspect, selected file bytes for get, a standard ZIP archive for export, and continuing a saved project for status. It implicitly separates itself from the write tool ("Generation and effects are explicit workspace.write actions") but never names the sibling outright, and the opening sentence packs two different operations into one clause, which blurs the single-purpose read.

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?

"Use get/status to continue a saved workspace project" gives a real when-to-use cue, and the closing sentence steers generative/mutating work to workspace.write. However, there is no guidance on choosing between inspect versus get versus export, and no stated preconditions or exclusions for the review_url/preview_url access paths.

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