Skip to main content
Glama

Show Site Preview

show_site_preview
Idempotent

Show the user's website inside the chat as a live preview panel (on AI apps that support interactive panels; elsewhere it returns a preview link to share). Renders the CURRENT DRAFT — call it when the user asks to see their site, or once after finishing a batch of edits so they can see the result; every edit tool already returns a fresh preview_url, so prefer ONE preview call after several edits over one per edit. Refreshing re-renders the draft preview (the same staging refresh every edit performs). The response includes the page list and publish readiness: when publishing isn't included on the site's plan, can_publish is false and the response carries a link to relay (its shape varies by host) — share it if the user wants to go live (don't retry publish_site).

Annotations: read-only=false, destructive=false, idempotent=true, open-world=false. Why: A write, not a read: it regenerates the draft's staging preview so the panel can show it. Not destructive — only a derived copy is rewritten, no user content changes, nothing goes live. Idempotent; closed-world.

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": "show_site_preview"
  }
}

Input Schema

NameRequiredDescriptionDefault
site_idYesThe site to preview

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already flag it as a non-destructive, idempotent write, and the description adds genuine context beyond that: it explains the write exists because it regenerates the draft's staging preview, and that nothing goes live. It also discloses the response payload (page list and publish readiness) and the host-dependent fallback (a shareable preview link on apps without interactive panels).

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-loaded with the action and then the when-to-call rules, with no filler sentences. It is dense and slightly long, but the parentheticals (panel support, staging refresh) each carry real decision-relevant information rather than restating the name.

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 one-parameter tool with no output schema and already-rich annotations, it covers what is rendered, when to call it, how often, what the response contains, and how to handle the can_publish=false case across differing hosts. Nothing an agent needs 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?

There is a single parameter (site_id) at 100% schema coverage, with the schema already saying 'The site to preview' and enforcing a UUID pattern. The prose only indirectly adds meaning by clarifying that the site's current draft is what gets rendered; it never discusses the parameter itself, so baseline 3 is right.

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 and resource ('Show the user's website inside the chat as a live preview panel') plus the exact artifact rendered ('the CURRENT DRAFT'), which separates it from get_site/publish_site and from the edit tools that also produce preview URLs. An agent knows what this returns 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 explicit triggers ('when the user asks to see their site', 'once after finishing a batch of edits') and an explicit rate/anti-pattern rule: prefer ONE preview call after several edits over one per edit, since every edit tool already returns a fresh preview_url. It also names what not to do — 'don't retry publish_site' — when can_publish is false.

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.