Skip to main content
Glama
vuluu2k

sbuilder-mcp

by vuluu2k
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

sb_import_site

Read a site's sitemap or page links to generate draft pages from your tokens. Dry run returns the page list before creation.

Instructions

Read a WHOLE site from one URL — its sitemap, or the links on that page — and give each page found its own DRAFT page here, built from this site's tokens. Not a clone. Dry run returns the page list before anything is created.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
navNoShared header linking the new pages, default true
urlYesAny page of the site
depthNoNo sitemap: link depth, default 1
dry_runNo
excludeNo
includeNoPath substrings to keep
site_idNo
homepageNoEntry into this site's home page, default true
max_nodesNoPer page, default 300
max_pagesNoDefault 12
max_imagesNoDefault 24, whole import
upload_imagesNo
nav_timeout_msNoHow long to wait for a page to answer at all. Default 30000; raise it for a slow origin

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.39.0
    • addedInput schema / properties / nav_timeout_ms
      Added value: +{
+  "description": "How long to wait for a page to answer at all. Default 30000; raise it for a slow origin",
+  "maximum": 120000,
+  "minimum": 5000,
+  "type": "integer"
+}
  2. Addedv0.25.0

TDQS

A4/5.0
Behavior4/5

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

Annotations mark it as a write (readOnlyHint=false), open-world, non-destructive, but the description adds meaningful context beyond them: output pages are DRAFTS, not published, and dry_run returns the page list before any creation occurs. It does not cover auth requirements or rate/timeout behavior, keeping it below the top band.

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 short, front-loaded sentences: action and scope first, the clone caveat second, the dry-run behavior last. No filler, and every clause carries information the agent needs.

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 complex 13-parameter import with no output schema, the description covers the core concept (source, draft output, dry-run preview) adequately. It omits detail on many knobs (include/exclude, image handling, limits), but the essential mental model for invoking it correctly is present.

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 69% across 13 parameters, so the schema does most of the documentation. The description adds only indirect meaning — the sitemap-vs-links sourcing hint relates to depth, and the dry-run sentence relates to dry_run — while most parameters remain unexplained in prose. Baseline 3 is appropriate.

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 gives a specific verb and resource ('Read a WHOLE site from one URL'), explains the sourcing mechanism (sitemap or page links), and states the output artifact (a DRAFT page per page found). It also explicitly contrasts the behavior with a clone, letting an agent separate it from a copying/duplication tool.

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?

It implies usage through the dry-run note ('Dry run returns the page list before anything is created'), which tells the agent a preview path exists, but it never names alternatives (e.g. sb_import vs sb_page_create) or states when-not to use this tool. Guidance is inferred rather than explicit.

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

Deploy Server

Other Tools