Maps by DeltaBreen

map_code

Idempotent

What puts a dashboard map on a site: the tag to paste (one element and one script, for any site or builder that takes HTML: Squarespace, Webflow, Shopify, Framer and others), the shortcode for a WordPress site with our plugin (which brings its own key), the map's own page and frame code when it is shared (for Google Sites, Notion and link-in-bio pages), and a style URL for MapLibre apps (Flutter, iOS, Android) that draws the map with its pins. Give site: a publishable key that already lets that site in is used, else one is made for it when the caller owns the workspace and may manage keys; at the plan's number of keys the site is added to one the workspace has.

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": {
      "map_id": "<map_id>"
    },
    "name": "map_code"
  }
}

Input Schema

Name	Required	Description	Default
`site`	No	The site the map goes on, e.g. "example.com": a publishable key that lets it in is used, or (workspace owner) made for it.
`map_id`	Yes	The map's id (uuid), from list_maps or create_map.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 30, 2026

TDQS

A3.8/5.0

Behavior4/5

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

The description discloses a real side effect not derivable from annotations: it may mint a publishable key, requires workspace ownership plus key-management permission to do so, and falls back to attaching the site to an existing workspace key when the plan's key count is reached. That explains the `readOnlyHint: false` annotation and warns of a resource-creating path. It stops short of describing key/site validation failure modes.

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 front-loaded artifact list is well ordered, but the whole description is one extremely long nested sentence with four parenthesized platform lists and a trailing conditional clause about key provisioning. It is dense and would be far more scannable as a short bulleted list; length is not justified for a 2-parameter tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

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 burden of explaining the return value, and it flags the four artifact kinds but never says whether all are returned together or how they are shaped (plain strings? object with named fields?). For a read-style code-generation tool with no output schema, that leaves a meaningful gap despite strong coverage of inputs and side effects.

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 100%, so the baseline is 3; the description earns above that by adding the plan-limit fallback and ownership/permission conditions for `site` that the schema's shorter description omits. It adds nothing new for `map_id` (the schema already points at list_maps/create_map), so it is not a full 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description enumerates the concrete artifacts produced — HTML tag + script, WordPress shortcode, shared map page/frame code, and a MapLibre style URL — which tells an agent exactly what it gets back. The verb is implicit ('What puts a dashboard map on a site') rather than stated as 'generate', and it never acknowledges the sibling `snippet` tool, so the agent cannot fully disambiguate between the two.

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?

It routes by platform: HTML for Squarespace/Webflow/Shopify/Framer, the shortcode for a WordPress site with the plugin, shared page/frame code for Google Sites/Notion/link-in-bio, and the style URL for MapLibre apps (Flutter/iOS/Android). That is genuinely useful conditional context, though it never states when to prefer this over `snippet` or what happens if the caller's platform isn't listed.

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

All Maps by DeltaBreen tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?