Make printable recipe cards from your own recipes as a print-ready PDF.
Scored across 1 tool
There is only one tool, so there is no possibility of misselection between overlapping operations. The tool's purpose is stated unambiguously with clear trigger phrases and explicit non-goals (no recipe finding, no nutrition).
The single name 'generate_recipe_cards' follows a clean verb_noun convention that precisely matches the operation performed. There are no competing conventions to create inconsistency.
A single tool is thin for a server, though this one is substantial and internally handles many variants (card sizes, scaling, pagination). It is not trivial, but the surface offers no separate operations an agent could compose.
The card-generation lifecycle (scale, format, layout, PDF output) is covered end-to-end within a deliberately narrow scope. Minor gaps exist, such as no way to retrieve or re-list previously generated cards or inspect available templates separately.
Use this when the user wants printable recipe cards ("recipe card", "recipe cards printable", "4x6 recipe card", "recipe card template", "3x5 recipe cards", "print my recipe on a card") or wants a recipe doubled, halved or scaled to a number of servings for printing. If the user pastes or uploads a recipe (text, a web page or a photo of a card), first copy its title, servings, ingredient lines and steps into recipes, keeping amounts as written, then call. Builds a PDF of 4x6, 3x5, 5x7, half-letter or A6 cards, up to 4 per Letter or A4 sheet with cut lines or one per page, scales amounts with fractions kept as fractions, converts units only when asked, and continues long recipes on a second card instead of shrinking text below 8 pt. Returns the scaled ingredient lines, card counts and a PDF link. Does not find or invent recipes, does not compute nutrition, and does not change cooking times.
| Name | Required | Description | Default |
|---|---|---|---|
| from | No | Optional footer name, printed as "From the kitchen of <name>", e.g. "Grandma Rose". | |
| color | No | Accent colour: hex like #C2410C or a name (terracotta, red, rose, berry, purple, blue, navy, teal, green, sage, olive, mustard, brown, slate, black). Default terracotta. | |
| paper | No | letter (default; 2 to 4 cards per sheet with cut lines), a4, or card (one card per page at true size, for card stock). Default a4 for A6 cards. | |
| scale | No | Scale every recipe by this factor instead: 2 (double), 0.5 (half), 1.5 or "3/4". Amounts stay fractions, e.g. 3/4 cup x 2 = 1 1/2 cups. | |
| steps | No | Only when sending one recipe without the recipes list: its steps. | |
| title | No | Only when sending one recipe without the recipes list: its name. | |
| units | No | keep (default, amounts as written), metric (ml, l, g, kg) or us (cups, tbsp, tsp, oz, lb). Converts volume to volume and weight to weight only. | |
| recipes | No | The recipes, one object each with title, servings, ingredients and steps. If the user pasted or photographed a recipe, copy its title, servings, ingredient lines and steps into these fields first; keep amounts exactly as written. | |
| scale_to | No | Same as servings: the target number of servings, e.g. 12. | |
| servings | No | Scale every recipe to this many servings, e.g. 12. Each recipe needs its own servings to scale from. | |
| card_size | No | 4x6 (default), 3x5, 5x7, half-letter (5.5x8.5 in) or a6. | |
| ingredients | No | Only when sending one recipe without the recipes list: its ingredient lines. | |
| orientation | No | landscape (default for 4x6, 3x5, 5x7) or portrait (default for half-letter and A6). | |
| recipe_text | No | Fallback: a whole recipe pasted as plain text (title on the first line, then Ingredients and Instructions sections). Use recipes when you can. |
| Name | Required | Description |
|---|---|---|
| kind | Yes | |
| notes | Yes | |
| paper | Yes | |
| units | Yes | |
| accent | Yes | |
| inputs | Yes | |
| recipes | Yes | |
| card_size | Yes | |
| downloads | Yes | |
| card_count | Yes | |
| page_count | Yes | |
| card_inches | Yes | |
| orientation | Yes | |
| recipes_count | No | |
| cards_per_page | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare a safe, idempotent, non-open-world read, so the bar is low, yet the description adds substantial behavior: fractions preserved rather than decimalized, unit conversion only on request, long recipes spilling to a second card instead of shrinking below 8 pt, cut lines, and returned scaled lines plus card counts and a PDF link. That is real operational context an agent could not infer from the hints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The trigger phrase and the main action are front-loaded, and each sentence carries either a trigger, a preprocessing rule, or a behavior. It is dense but readable; the parenthetical list of card phrasings and the return-value sentence are slightly padded given an output schema exists.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 14-parameter tool with optional everything, the description covers the decision to call, the ingestion path for pasted or photographed recipes, supported sizes and layouts, scaling and unit rules, and explicit non-goals. With an output schema present, the brief return summary is sufficient rather than necessary.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents card_size, paper, units, scale, orientation and the single-recipe shortcut fields. The description's mentions of the same card sizes and the keep/metric/us behavior largely restate the schema, adding only the 4-per-sheet and 8 pt layout constraints, which the paper field already gestures at. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and artifact ("Builds a PDF of 4x6, 3x5, 5x7, half-letter or A6 cards") plus the scaling function, and explicitly delimits scope with "Does not find or invent recipes, does not compute nutrition, and does not change cooking times." An agent knows exactly what this produces without opening the schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It opens with an explicit trigger list ("recipe card", "4x6 recipe card", "print my recipe on a card", doubled/halved/scaled for printing) and gives a concrete pre-call procedure: copy title, servings, ingredient lines and steps into recipes, keeping amounts as written. Negative conditions (no recipe invention, no nutrition, no time changes) rule out the closest misuses.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
generate_recipe_cardsMake printable business cards from your name and contact details.
Make packing slips for your small business orders and print them in one go.
Turn a PDF into a booklet you can print at home, fold in half and staple on the fold.
Make a printable habit tracker for any month as a print-ready PDF.
Add one secure layer between your agents and this server.