Skip to main content
Glama

Your AI Kitchen (YAK)

by com.youraikitchen
OverviewDiscussionsAdmin

File a finished draft

finalize_recipe
Destructive

Turn a draft into a saved recipe: sets status final, infers filing, applies the sharing default, estimates nutrition. DESTRUCTIVE: the user's other same-title drafts from the last 6 hours go to trash (not erased; restore with delete_recipe action=restore within 7 days). Not idempotent. Needs 1+ ingredient and step; blocked on read-only accounts. Returns {id, title, filed, assumed, closed_duplicate_drafts?}.

Input Schema

NameRequiredDescriptionDefault
idYesDraft recipe id (UUID) returned by start_recipe_draft or search_recipes status=draft, e.g. "3f2b8c1e-7a4d-4e0b-9c55-1d2e3f4a5b6c". Required.
titleNoOptional final title, plain text, max 200 chars, e.g. "Nonna's Sunday Sauce". Defaults to the draft title with a trailing "(draft)" removed.
visibilityNoOptional. "private" = only the user; "family" = shared with family_group_id. Omit to apply the user's sharing default, e.g. "private".
inspired_byNoOptional sources this recipe riffs on, e.g. [{"title": "Serious Eats carbonara", "url": "https://www.seriouseats.com/..."}].
menu_entry_idNoMenu slot to fill once saved
family_group_idNoOptional group id (UUID) from manage_family action=list; only used with visibility="family", e.g. "9a1c0e2d-4b3f-4c6a-8d7e-0f1a2b3c4d5e".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / properties / family_group_id / description
      Previous value: -"Group id (from manage_family list) when visibility is family"New value: +"Optional group id (UUID) from manage_family action=list; only used with visibility=\"family\", e.g. \"9a1c0e2d-4b3f-4c6a-8d7e-0f1a2b3c4d5e\"."
    • changedInput schema / properties / id / description
      Previous value: -"Draft id (UUID) from search_recipes or an earlier result"New value: +"Draft recipe id (UUID) returned by start_recipe_draft or search_recipes status=draft, e.g. \"3f2b8c1e-7a4d-4e0b-9c55-1d2e3f4a5b6c\". Required."
    • changedInput schema / properties / inspired_by / description
      Previous value: -"Sources it riffs on: [{title, url}]"New value: +"Optional sources this recipe riffs on, e.g. [{\"title\": \"Serious Eats carbonara\", \"url\": \"https://www.seriouseats.com/...\"}]."
    • addedInput schema / properties / inspired_by / items / properties
      Added value: +{
+  "title": {
+    "description": "Source name, e.g. \"Serious Eats carbonara\"",
+    "type": "string"
+  },
+  "url": {
+    "description": "Optional https URL of the source",
+    "type": "string"
+  }
+}
    • changedInput schema / properties / title / description
      Previous value: -"Final title; defaults to the draft title without \"(draft)\""New value: +"Optional final title, plain text, max 200 chars, e.g. \"Nonna's Sunday Sauce\". Defaults to the draft title with a trailing \"(draft)\" removed."
    • changedInput schema / properties / visibility / description
      Previous value: -"private = only the user; family = shared with family_group_id. Default: the user's sharing default"New value: +"Optional. \"private\" = only the user; \"family\" = shared with family_group_id. Omit to apply the user's sharing default, e.g. \"private\"."
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the destructiveHint annotation to specify exactly what is destroyed (other same-title drafts from the last 6 hours), that it is recoverable within 7 days via a named sibling action, non-idempotency, restrictions, and the return shape. This is exactly the behavioral context an agent needs before invoking a destructive mutation.

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?

Dense but front-loaded: the core action comes first, the DESTRUCTIVE warning is capitalized and scoped, and the return contract closes it out. Nearly every clause carries distinct information with no padding.

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?

For a destructive mutation with no output schema, the description covers preconditions, side effects, recoverability, non-idempotency, and return fields. Nothing essential to correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all six parameters are already documented. The description adds only marginal meaning (default title behavior, sharing default, the 1+ ingredient/step constraint) rather than syntax or format detail beyond the schema — baseline 3 applies.

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 ('turn a draft into a saved recipe') and enumerates the concrete effects (status final, infers filing, applies sharing default, estimates nutrition). This clearly distinguishes it from siblings like save_recipe, start_recipe_draft, and get_recipe without opening any schema.

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?

Gives clear context for use — finishing a draft — plus prerequisites (1+ ingredient and step, blocked on read-only accounts) and a recovery alternative (delete_recipe action=restore) for the destruction it causes. It stops short of an explicit 'use this instead of X when...' comparison against save_recipe or update_recipe, so not a full 5.

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

All Your AI Kitchen (YAK) 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