Skip to main content
Glama

search_recipes

Read-only
Search Recipe Reels' catalog of recipes extracted from cooking videos.
Every filter is optional and they combine with AND; an unknown value
simply matches nothing. Without a session token this searches the
public catalog exactly as a logged-out visitor would. Results come
back newest first, each with its nutrition per serving, cost per
serving and `created_at` (when it was imported). Pass a result's `id`
to get_recipe for the full ingredients and steps.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_recipes"
  }
}

Input Schema

NameRequiredDescriptionDefault
dietNoA diet tag, e.g. vegetarian, vegan, keto, low-carb, high-protein.
mealNobreakfast, lunch, dinner or snack.
mineNoTrue to search only the connected account's own recipes (My Recipes). Needs session_token.
timeNoTotal prep + cook time: 10min, 30min or 1hour (that long or less), or slow_cook (over 1 hour).
limitNoHow many results to return, 1 to 50.
styleNoone_pot, sheet_pan, meal_prep, kid_friendly, party_food or date_night.
budgetNoUnder this many US dollars per serving (an estimate from Kroger-family store prices, pantry staples excluded).
courseNoentree, side, dessert, beverage or appetizer.
creatorNoA video creator's name, exactly as `creator_name` shows it on a recipe.
holidayNothanksgiving, christmas, new_years, valentines_day, easter, fourth_of_july, halloween, game_day or cinco_de_mayo.
proteinNoAt least this many grams of protein per serving.
beverageNoDrink type: coffee, tea, cocktail, smoothie, juice, milkshake or hot_chocolate.
caloriesNoUnder this many calories per serving.
platformNoWhere the video came from: Youtube, TikTok, Instagram, Facebook or Pinterest.
video_idNoA video's own id (`source_video_id`), used with `platform` to find every recipe split from that one video. Needs a session token (any registered account).
dish_typeNosoup, stew_chili, salad, sandwich, wrap_burrito, tacos, burger, pizza, casserole, stir_fry, curry, bowl, dip, sauce_dressing, bread, cookies_bars, cake_cupcakes or pie.
ingredientsNoAt most this many ingredients, not counting pantry staples.
nationalityNoCuisine: indian, western, south_american, korean, chinese, italian, mexican, japanese, mediterranean or thai.
cooking_typeNostovetop, oven, grill, crockpot, air_fryer, pressure_cooker, smoker, deep_fryer, microwave or no_cook.
session_tokenNoOptional: the session token check_agent_connection returned (or send it as an Authorization: Bearer header). Omit it to act as a logged-out visitor.
main_ingredientNochicken, ground_beef, beef, pork, sausage, bacon, turkey, salmon, shrimp, fish, tofu, eggs, pasta, rice, potatoes, beans_lentils, cheese, vegetables or fruit.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / platform / description
      Previous value: -"Where the video came from: Youtube, TikTok, Instagram or Facebook."New value: +"Where the video came from: Youtube, TikTok, Instagram, Facebook or Pinterest."
  2. Changed1 schema field changed
    • changedInput schema / properties / budget / description
      Previous value: -"Under this many US dollars per serving (an estimate from one reference store's prices, pantry staples excluded)."New value: +"Under this many US dollars per serving (an estimate from Kroger-family store prices, pantry staples excluded)."
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say read-only and closed-world; the description adds substantial context beyond that: unauthenticated calls search the public catalog as a logged-out visitor, results are ordered newest-first, each result carries nutrition per serving, cost per serving, and created_at meaning import time. It also flags that `mine` and `video_id` require a session token, which is real behavioral disclosure.

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

Conciseness4/5

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

About five sentences for a 21-parameter tool is efficient, and the core action plus filtering semantics are front-loaded. There is minor overlap with the session_token schema text, and the dense unbroken paragraph makes the return-shape information slightly harder to scan.

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?

With no output schema, the description usefully sketches what comes back (nutrition per serving, cost per serving, created_at, newest-first ordering) and tells the agent how to escalate to get_recipe. For a large but all-optional filter tool, nothing essential to correct invocation appears missing.

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 100%, so the per-filter vocabulary is already documented; the description adds cross-parameter meaning that the schema does not, namely that filters are optional, combine with AND, and that an unrecognized value simply matches nothing. It also ties `video_id` to `platform` and `mine` to session presence.

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?

States a specific verb and resource ('Search Recipe Reels' catalog of recipes extracted from cooking videos') and implicitly distinguishes itself from get_recipe by noting that a result's id must be passed to get_recipe for full ingredients and steps. An agent can tell this is the browse/filter entry point versus the detail-fetch sibling.

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?

Clearly explains filter semantics (all optional, AND-combined, unknown values match nothing) and routes to get_recipe for detail, which is the key alternative in the sibling set. It does not explicitly state when not to use it (e.g., when you already have a recipe id), but the context is otherwise clear.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources