Skip to main content
Glama

Blawgy

by com.blawgy
OverviewDiscussionsAdmin

List existing pages

list_existing_pages
Read-onlyIdempotent

The pages Blawgy knows the site already has outside the articles Blawgy wrote (found in the sitemap, feeds, Search Console, or imported), with what each page answers when known (ownedIntent, primaryKeyword) and its kind (article, help, product, category, landing, other, unknown; help = product docs and help-center pages, checked like articles but never suggested for a refresh). Includes counts by kind and source, how many were removed, and when the inventory last synced. Filter by kind (also skipped: pages new ideas are never checked against, such as products, listings, legal and sign-up pages; removed: pages removed with remove_existing_page), by origin (import = added by the customer) or a search string (URL, title or what the page answers); page with limit/offset. Free.

Input Schema

NameRequiredDescriptionDefault
kindNoOnly pages of this kind, or skipped / removed
siteYesThe site to act on. One of: fencestainingdenver.com.
limitNoMax pages to return (default 50, max 200)
offsetNoSkip this many pages (for paging)
originNoOnly pages from this source (import = added by the customer)
searchNoSubstring match on URL, title or what the page answers

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / kind / description
      Previous value: -"Only pages of this kind"New value: +"Only pages of this kind, or skipped / removed"
    • changedInput schema / properties / kind / enum
      Previous value: -[
-  "article",
-  "product",
-  "category",
-  "landing",
-  "other",
-  "unknown"
-]New value: +[
+  "article",
+  "help",
+  "product",
+  "category",
+  "landing",
+  "other",
+  "unknown",
+  "skipped",
+  "removed"
+]
    • addedInput schema / properties / origin
      Added value: +{
+  "description": "Only pages from this source (import = added by the customer)",
+  "enum": [
+    "sitemap",
+    "rss",
+    "gsc",
+    "import",
+    "cms"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / search / description
      Previous value: -"Substring match on URL or title"New value: +"Substring match on URL, title or what the page answers"
  2. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds genuinely new behavioral context: pages are sourced from sitemap/feeds/GSC/import, help pages are checked like articles but never suggested for refresh, counts by kind and source plus last-sync time are returned, and the call is free.

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 resource definition before diving into filters, and nearly every clause carries information. It is a dense single block of parentheticals rather than scannable structure, which slightly hurts readability, but there is little outright waste.

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?

With no output schema, the description carries the return-value burden and does so: it names the per-page fields (ownedIntent, primaryKeyword, kind), the aggregate counts by kind/source, the removed count, and sync timestamp, plus paging via limit/offset. An agent has everything needed to call it correctly.

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 100%, so baseline is 3, but the description earns extra by explaining enumeration values beyond the terse schema text: `skipped` pages are 'never checked against' by new ideas (products, listings, legal, sign-up), `removed` pages were deleted via remove_existing_page, and search matches URL, title, or owned intent.

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 (list) and resource (existing pages Blawgy knows the site has), and sharply scopes it against the sibling list_articles by defining these as pages 'outside the articles Blawgy wrote'. It further enumerates sources (sitemap, feeds, Search Console, import) so the agent understands exactly what set is returned.

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?

The description clarifies filter semantics (what `skipped` and `removed` mean, `import` = added by the customer) and references remove_existing_page, which helps routing. However it never states explicitly when to call this tool versus alternatives like list_articles or sync_existing_pages, leaving the primary when-to-use decision implied.

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

All Blawgy toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources