Skip to main content
Glama

roastify-mcp

by io.github.lonniev

roastify_generate_artwork

Generate packaging artwork from one of your saved Design Studio designs.

This personalizes a template you already authored: it rewrites that design's named text and image placeholders. It cannot author a design from scratch, and the artwork it produces is NOT attached to a product — Roastify's API has no product-create or storefront-sync surface. You get an artwork URL and carry it onward yourself.

Roastify renders asynchronously, so this returns a job id straight away. Check it with roastify_artwork_status, which is free.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
npubNoRequired. Your Nostr public key (npub1...) for credit billing.
fieldsYesPlaceholders to rewrite, each {"fieldId": "placeholder_title", "type": "text"|"image", "value": "..."}. An image value must be an https:// URL.
dpop_tokenNo
product_idYesA saved design's id, from list_my_products.
client_req_idNoYour own idempotency key. Reusing it makes a repeated request safe — Roastify will not generate the artwork twice.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations, the description carries the full burden of behavioral disclosure, and it does so well: it reveals asynchronous rendering (returns a job id, not artwork), the need to poll status, the non-persistence of the artwork to a product, and the limitation to template personalization. This goes well beyond a generic 'generate artwork' statement.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short paragraphs, each earning its place: purpose, constraints/limitations, and async behavior with the follow-up pointer. Information is front-loaded in the first sentence, and there is no wasted prose.

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?

Given the large sibling set and the presence of an output schema, the description covers the essentials: what the tool can and cannot do, the prerequisite (saved design), the async workflow, and the exact follow-up tool. An agent can select and invoke this tool correctly without additional research.

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 80%, and the description adds meaningful semantics for the key parameters: product_id is sourced from list_my_products, fields is explained with an inline structure example and the https requirement for image values, and client_req_id's idempotency behavior is described. Only dpop_token is left unexplained, preventing a 5.

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 opens with a specific verb+resource: 'Generate packaging artwork from one of your saved Design Studio designs.' It then clarifies that the tool rewrites placeholders in an existing template rather than authoring from scratch, which distinguishes it from design-creation siblings like roastify_add_design_element or roastify_update_design_text.

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?

Explicitly states when to use it — when you have a saved Design Studio design to personalize — and what it cannot do ('cannot author a design from scratch', 'NOT attached to a product', 'no product-create or storefront-sync surface'). It also names the exact follow-up tool and its cost profile: 'Check it with roastify_artwork_status, which is free.'

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

All roastify-mcp toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.4/5.0
Disambiguation4/5

Most tools target clearly distinct resources—patron balances vs. operator Authority balances, design text vs. full design fetches, operator vs. patron credentials—and the verbose descriptions carefully separate request/receive flows. A few pairs could still be confused at a glance, such as service_status/session_status, forget_coupon/delete_coupon, and get_design_text/fetch_design.

Naming Consistency4/5

All tools share the roastify_ snake_case prefix and mostly follow a verb_noun pattern like list_, get_, update_, delete_, and create. However, several noun-only names (service_status, session_status, account_statement, oracle_about) and the inconsistent forget_ vs. delete_ distinction for credential/coupon removal keep it from being fully consistent.

Tool Count1/5

69 tools is an extreme count for a single MCP surface and far exceeds the 25+ threshold. Even though the tools span many subdomains—design, payments, coupons, credentials, pricing, notarization, oracle—the sheer number will be heavy on agent context and selection accuracy.

Completeness3/5

Core workflows are largely covered: design storage/editing, coupon lifecycle, credential vaults, credit purchasing, pricing models, notarization, and the oracle all have reasonable read/write surfaces. However, session_status explicitly tells not_registered operators to call register_operator, which does not exist in the tool set, and design editing lacks any delete-element operation, leaving notable dead ends.

Resources