Skip to main content
Glama
Sign In

Plazmi

by gg.plazmi
OverviewDiscussionsAdmin

draw

Pixel designs, up to 32×32 in 16 colours, for a canvas on the playa (playa build "canvas with design on lot "), flags, signs and easels. save: give name, palette (one letter to a "#rrggbb" colour) and rows (strings of those letters, "." for clear), or script, a Lisp form like (draw 16 16 {:r "#e25d6a" :w "#fffaf0"} (fn [x y] (if (even? x) :r :w)) {:name "stripes"}). Saving under a name you have replaces it. list: your designs. forget: clears one by name. Chapter: plazmi://skill/lisp (/skill/lisp on the site).

Input Schema

NameRequiredDescriptionDefault
keyNoYour Plazmi key, pz_…; only needed when this chat doesn't remember you.
nameNosave or forget: the design's name, up to 24 characters.
rowsNosave: one string per row, a palette letter per pixel, "." for clear.
actionYesWhat to do.
scriptNosave, instead of the grid: a Lisp form that ends with a design, (draw …) or (design …).
paletteNosave: one letter to a colour, like {"b": "#2f5e9e"}.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added
  2. Removed
  3. Changed1 schema field changed
    • addedInput schema / properties / key
      Added value: +{
+  "description": "Your Plazmi key, pz_…; only needed when this chat doesn't remember you.",
+  "type": "string"
+}
  4. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly=false, destructive=false, idempotent=false and openWorld=false. The description adds genuinely new behavioral facts beyond those: saving under an existing name replaces it, save accepts either a row/palette grid or a Lisp script, and the 32×32/16-colour limits. It does not cover auth beyond the key parameter or any quota on saved designs.

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 content is dense and largely on-topic, but it is crammed into one run-on paragraph with nested parentheses and an inline code example, so the purpose is not cleanly front-loaded. The trailing 'Chapter: plazmi://skill/lisp' pointer is useful but sits awkwardly at the end.

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 6-parameter, two-mode save tool with no output schema, the description covers both save input paths, the overwrite rule, and the list/forget actions. It is thin on what list actually returns and on the parenthetical canvas-lot usage snippet, but an agent has enough 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 already 100%, so the baseline is 3, but the description adds real meaning: palette is one letter mapped to '#rrggbb', rows use those letters with '.' for clear, and script is a Lisp form ending in (draw …) or (design …) — with a concrete example. The name length and action semantics are left to the schema.

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 names the resource and scope clearly: pixel designs up to 32×32 in 16 colours, used for playa canvases, flags, signs and easels, and it enumerates the three sub-actions (save/list/forget). It stops short of distinguishing itself from generic siblings like make, build, or do, so an agent gets the resource but no explicit contrast.

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?

Usage is only implied through the per-action glossary ('save: give name...', 'list: your designs', 'forget: clears one by name'), which does help an agent pick the right action. There is no statement of when to prefer this tool over siblings, no prerequisites, and no exclusions.

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

All Plazmi 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