Skip to main content
Glama
Sign In

Mondovo

by com.mondovo.app
OverviewDiscussionsAdmin

Make a campaign landing page

spawn_campaign_landing_page

Have our AI write a campaign landing page for one strategy cell whose headline is the cell's hook, subhead its promise and first proof point its proof — so the page says exactly what the ad said — and save it as a DRAFT page at /lp/{slug}. The cell needs a messaging brief first. Pass campaign_id to link it to a campaign of this site. Nothing goes live and no build starts. Counts toward the hourly AI limit. ON A SITE THAT STILL HOLDS SEVERAL DESIGNS this builds the site: Mondovo copies the chosen design into the working site (or reuses the copy made earlier), adds to that, and the response carries its new site_id and a build_transition — relay its tell_user and use the new site_id from then on. Pass variation_id for the design the user picked; omitted, Mondovo uses the design already built or the only one edited, and otherwise answers choose_design so you can ask the user.

Input Schema

NameRequiredDescriptionDefault
goalNoWhat the page asks the visitor to do
slugNolowercase-with-hyphens; default derived from the cell
titleNo
site_idYesThe site, from list_sites
cell_keyYesA strategy cell: "persona_id:stage_id:pain_id" or "persona_id:stage_id:pain_id:competitor_id", ids from get_marketing_strategy
user_goalNoOptional: the user's goal behind this call, in one short sentence of plain words (e.g. "add a page so customers can book tables"). No names, emails or other personal details.
campaign_idNoA campaign of this site, from list_marketing_campaigns
variation_idNoOn a site that still holds several designs: the design to build the site from (from list_variations). Mondovo copies it into the working site and adds to that. Omit on a site that is already built.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / user_goal
      Added value: +{
+  "description": "Optional: the user's goal behind this call, in one short sentence of plain words (e.g. \"add a page so customers can book tables\"). No names, emails or other personal details.",
+  "type": "string"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / variation_id
      Added value: +{
+  "description": "On a site that still holds several designs: the design to build the site from (from list_variations). Mondovo copies it into the working site and adds to that. Omit on a site that is already built.",
+  "maxLength": 200,
+  "type": "string"
+}
  3. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Adds substantial context beyond the annotations: nothing goes live, no build starts, it counts toward the hourly AI limit, and on multi-design sites it copies a design, mutates the site, and returns a new `site_id` plus `build_transition` whose `tell_user` must be relayed. That is exactly the kind of side-effect disclosure annotations cannot carry (destructiveHint=false alone would understate the site-copy behavior). A small deduction for not clarifying what happens to existing pages or whether the call fails or partially succeeds on error.

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 opening sentence is a long run-on with em-dashes that delays the core statement, and the ALL-CAPS block 'ON A SITE THAT STILL HOLDS SEVERAL DESIGNS' is an awkward structural device. Content is dense with little filler, but the front-loading and sentence hygiene are weak for a definition this long.

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 an 8-parameter, no-output-schema mutation tool, the description covers the critical unknowns: draft-only behavior, rate-limit cost, and the response fields (`site_id`, `build_transition`, `choose_design`) the agent must react to. Gaps remain around the goal enum, title, and user_goal, and around failure/partial-success handling.

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 coverage is already 88%, so the baseline is 3; the description adds meaning by explaining that campaign_id links the page to a campaign of this site, that slug becomes the /lp/{slug} path, and by elaborating the omit-vs-supply semantics of variation_id. It does not mention goal, title, or user_goal at all, but those are well documented in the schema.

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 ('Have our AI write a campaign landing page for one strategy cell') plus the exact output artifact (a DRAFT page at /lp/{slug}), which separates it from generic page creators like add_page or create_page_draft in the sibling list. The mapping of headline/subhead/proof point to the cell's hook/promise/proof is a concrete, distinguishing scope statement.

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?

Gives a hard prerequisite ('The cell needs a messaging brief first'), explains when to pass campaign_id, and explicitly covers the variation_id decision including the fallback that Mondovo answers `choose_design` so the agent can ask the user. It stops short of naming when to prefer add_page/create_page_draft instead, so it lacks a full when-not statement.

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

All Mondovo 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