Skip to main content
Glama
Sign In

Pugi

by io.pugi
OverviewDiscussionsAdmin

Make four logos

make_logo
DestructiveIdempotent

Use this when the person wants a logo or brand mark for a business, shop, product or project, for example "make a logo for Blue Fern Bakery". business_name must be the name the person gave, in their own words. If they gave no name, do not call this tool: ask them what the company is called, in their language (in Russian: «Как называется компания?»); never invent or translate a name. Pass their description and their own style words verbatim (never add style, colour or mood words yourself), and language (the language they write in). After a call, never describe what you passed to Pugi, name the tool or promise logos while a question is open; never say you passed something without calling. Pugi first asks the person to confirm the name in the card, once per name. If they say yes in words, call this tool again with the same business_name and the question_token. If they give another name in words, call this tool again with that business_name. A new business name is a new brand: never reuse another business's logo or answers. Pugi runs the same short brand interview as logo.pugi.io, one question per call (status needs_input), shown with its options in the card: tell the person in one short line to answer there or in their own words, without listing the options, then call again with their answer (trade for the first question, answers for the later ones). Use draw_now true only when the person says to draw now. Then it draws four whole logo options (PNG) the person can pick, change and use on a Pugi website. Generates logo design assets only. Do not use for photos, illustrations, posters, memes or editing an image the person uploaded; to change logos already shown in this conversation use refine_logo.

Input Schema

NameRequiredDescriptionDefault
nameNo
nicheNo
styleNoStyle words verbatim; styles also accepts a list.
tradeNoOnly after Pugi asked (status needs_input): the slug the user picked from the options, for example "coffee-shop", or their own words.
stylesNoThe user’s style words verbatim.
answersNoOnly after Pugi asked (status needs_input): every answer so far to its interview questions, the id Pugi gave and the user's words verbatim.
coloursNoOptional. Hex colours: {"primary": "#1e3a8a", "secondary": "#f59e0b", "text": "#111827"}, or a list of one to three of them in that order.
paletteNo
refinesNo
taglineNo
draw_nowNoTrue when the user wants the logos drawn now, without more questions.
industryNoOptional. What the business does, for example "coffee shop" or "accounting firm".
languageNoThe language the user is writing to you in, as a BCP 47 tag such as "uk", "de" or "pt-BR"; the questions come back in it.
name_proofNoSet by Pugi's card when the person confirms the name. Leave it out.
read_stateNoOnly with question_token: read what the logo card shows now (the drawn logos with their logo_id, or that the person is still answering). It only reads: it answers nothing for the person, draws nothing and charges nothing.
descriptionNoThe user’s description verbatim, including location, imagery and mood.
refine_notesNo
business_nameNoThe business name, as written by the user.
question_tokenNoOnly after Pugi asked (status needs_input): the question_token it returned. Pass it with the trade, the answers or draw_now; without it the brief starts again.
idempotency_keyYesA unique string for this call, reused only to retry it. The same key with the same arguments is never charged twice.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / read_state
      Added value: +{
+  "description": "Only with question_token: read what the logo card shows now (the drawn logos with their logo_id, or that the person is still answering). It only reads: it answers nothing for the person, draws nothing and charges nothing.",
+  "type": "boolean"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / name_proof
      Added value: +{
+  "description": "Set by Pugi's card when the person confirms the name. Leave it out.",
+  "maxLength": 64,
+  "type": "string"
+}
  3. Changed1 schema field changed
    • addedInput schema / properties / question_token
      Added value: +{
+  "description": "Only after Pugi asked (status needs_input): the question_token it returned. Pass it with the trade, the answers or draw_now; without it the brief starts again.",
+  "maxLength": 64,
+  "type": "string"
+}
  4. Changed1 schema field changed
    • addedInput schema / properties / language
      Added value: +{
+  "description": "The language the user is writing to you in, as a BCP 47 tag such as \"uk\", \"de\" or \"pt-BR\"; the questions come back in it.",
+  "maxLength": 35,
+  "pattern": "^[a-z]{2,3}(-[A-Za-z0-9]{2,8})?$",
+  "type": "string"
+}
  5. Changed2 schema fields changed
    • addedInput schema / properties / answers
      Added value: +{
+  "description": "Only after Pugi asked (status needs_input): every answer so far to its interview questions, the id Pugi gave and the user's words verbatim.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "answer": {
+        "maxLength": 240,
+        "minLength": 1,
+        "type": "string"
+      },
+      "id": {
+        "pattern": "^[a-z_-]{1,24}$",
+        "type": "string"
+      },
+      "question": {
+        "maxLength": 160,
+        "type": "string"
+      }
+    },
+    "required": [
+      "id",
+      "answer"
+    ],
+    "type": "object"
+  },
+  "maxItems": 8,
+  "type": "array"
+}
    • addedInput schema / properties / draw_now
      Added value: +{
+  "description": "True when the user wants the logos drawn now, without more questions.",
+  "type": "boolean"
+}
  6. Changed1 schema field changed
    • addedInput schema / properties / trade
      Added value: +{
+  "description": "Only after Pugi asked (status needs_input): the slug the user picked from the options, for example \"coffee-shop\", or their own words.",
+  "maxLength": 300,
+  "type": "string"
+}
  7. Changed16 schema fields changed
    • addedInput schema / anyOf
      Added value: +[
+  {
+    "required": [
+      "business_name"
+    ]
+  },
+  {
+    "required": [
+      "name"
+    ]
+  }
+]
    • changedInput schema / properties / business_name / description
      Previous value: -"The name the logos carry: 1 to 32 letters, digits, spaces or & ' . -"New value: +"The business name, as written by the user."
    • changedInput schema / properties / business_name / maxLength
      Previous value: -32New value: +60
    • changedInput schema / properties / description / description
      Previous value: -"Optional. A short description of the business."New value: +"The user’s description verbatim, including location, imagery and mood."
    • changedInput schema / properties / description / maxLength
      Previous value: -300New value: +400
    • addedInput schema / properties / name
      Added value: +{
+  "maxLength": 60,
+  "type": "string"
+}
    • addedInput schema / properties / niche
      Added value: +{
+  "maxLength": 300,
+  "type": "string"
+}
    • addedInput schema / properties / palette
      Added value: +{
+  "maxLength": 100,
+  "type": "string"
+}
    • addedInput schema / properties / refine_notes
      Added value: +{
+  "maxLength": 400,
+  "type": "string"
+}
    • addedInput schema / properties / refines
      Added value: +{
+  "items": {
+    "maxLength": 400,
+    "type": "string"
+  },
+  "maxItems": 20,
+  "type": "array"
+}
    • changedInput schema / properties / style / description
      Previous value: -"Optional. Default modern."New value: +"Style words verbatim; styles also accepts a list."
    • removedInput schema / properties / style / enum
      Removed value: -[
-  "minimal",
-  "tech",
-  "corporate",
-  "modern",
-  "playful",
-  "abstract",
-  "flashy"
-]
    • addedInput schema / properties / style / maxLength
      Added value: +400
    • addedInput schema / properties / styles
      Added value: +{
+  "description": "The user’s style words verbatim.",
+  "items": {
+    "maxLength": 400,
+    "type": "string"
+  },
+  "maxItems": 20,
+  "type": "array"
+}
    • addedInput schema / properties / tagline
      Added value: +{
+  "maxLength": 200,
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "business_name",
-  "idempotency_key"
-]New value: +[
+  "idempotency_key"
+]
  8. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare mutation, open-world and idempotency, and the description adds real behavior beyond them: Pugi asks for name confirmation once per name, runs one interview question per call returning status needs_input, and draws four PNG options the person can pick and use. It does not explain the credit cost of a draw or the shape of a successful response, which is a notable gap for a tool the schema says is never charged twice on retry.

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 when-to-use condition is front-loaded and the description is sized for a 20-parameter, multi-turn tool. However, several long semicolon-chained sentences mix tool behavior with agent policy (never describe what you passed, never promise logos, never say you passed something without calling), and the no-invented-name rule is repeated, so not every clause earns its place.

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?

There is no output schema, and the description still conveys the return flow: a needs_input status with a card, name confirmation, and four PNG logo options with logo_ids reachable via read_state. It stops short of enumerating the other status values or the success payload, which leaves some inference for a tool with this much branching behavior.

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?

With 20 parameters at 70% schema coverage, the description adds meaningful semantics: business_name must be the person's own wording and never invented or translated, description and style words are passed verbatim with no added mood or colour words, language is the language they write in, draw_now only when they say to draw now, and trade covers the first question while answers cover later ones. Some of this restates schema text (trade, draw_now, language), so it is not fully additive.

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 states a concrete verb and artifact: it draws four whole logo options (PNG) for a business, shop, product or project. It also scopes the tool negatively by ruling out photos, illustrations, posters, memes and uploaded-image editing, and names refine_logo as the sibling for changing logos already shown, so an agent can distinguish it without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit triggering conditions, a hard exclusion (no name given: ask, do not call), and a routing rule to refine_logo for already-shown logos. The multi-turn conditions are also spelled out: call again with the same business_name and question_token on verbal confirmation, or with a new business_name if the person renames.

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

All Pugi toolsInspect
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