Skip to main content
Glama

Draft a page for the chat

draft_page

Prepares a page the chat answers from (a title and the text), optionally as the answer to one unanswered question. Nothing is published: review_url opens the dashboard's page editor filled in, where the person checks it and saves it to publish. The draft link lasts 7 days. Needs the conversations permission and the store's switch for AI assistants in Settings > Security, and works only for stores the person owns.

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": {
      "store_id": "<store_id>",
      "title": "<title>",
      "body": "<body>"
    },
    "name": "draft_page"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesThe page's text, plain, with the facts the shop gave.
titleYes
languageNoThe page's language, e.g. 'en'.
store_idYesThe store's store_id (not its name).
question_idNoThe unanswered question it answers; saving the page marks it resolved.

Output Schema

NameRequiredDescriptionDefault
noteNo
savedYes
store_idYes
review_urlYes
expires_in_daysNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only say readOnly=false, destructive=false, idempotent=false, openWorld=false. The description adds substantive behavior beyond that: nothing is published, review_url opens a pre-filled dashboard editor where a human saves to publish, and the draft link expires after 7 days. It also discloses the permission and store-ownership gates, which annotations cannot express.

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

Conciseness5/5

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

Three sentences, front-loaded with what is produced, then the review/publish flow, then the access constraints. No filler; the expiry and permission details are compressed into a single clause each and every clause carries an actionable fact.

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 non-destructive draft-creation tool with an output schema already covering return values, the description covers the full agent-relevant surface: what is created, that it is not live, how a human publishes it, how long the link lives, and who may call it. Nothing needed to invoke it correctly is missing.

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 80%, so the schema already documents body, store_id, and question_id (including that saving resolves the question). The description restates "a title and the text" and the optional unanswered-question link without adding format or constraint detail for language or title beyond what the schema provides. Baseline 3 applies when the schema does the heavy lifting.

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 first sentence names a concrete verb and resource ("Prepares a page the chat answers from") and immediately scopes it as a draft with an optional question link. The follow-up "Nothing is published" separates this create-a-draft action from any publish path, so an agent can tell exactly what artifact it produces.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear preconditions: needs the conversations permission, the store's AI-assistant switch in Settings > Security, and works only for stores the person owns. It also states the optional link to one unanswered question. It stops short of naming a sibling alternative or an explicit when-not-to-use case, so it lands at 4 rather than 5.

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