Skip to main content
Glama

Menus

manage_menu
Destructive

Create, read, edit, share or delete the user's saved menus (undated; don't ask for dates). Reads: list, get. Writes (blocked on read-only accounts): save, add_entry, fill, set_entry, delete_entry, copy, rename, share. delete is permanent: ask, then confirm=true. Show the whole menu after get/save. Returns the menu {id, title, type, entries} or {menus:[...]}.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "manage_menu"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoMenu id (from list)
noteNoEntry note, max 500 chars
slotNobreakfast, lunch or dinner
typeNosave: week (Mon-Sun), day (breakfast/lunch/dinner) or occasion (by course)
labelNoadd_entry/set_entry: the user's dish name (e.g. "Salad") kept above the recipe link; set_entry with only label renames the dish
titleNosave/rename/copy: menu title
actionYesWhat to do
aislesNo{ingredient: aisle} for new list items
courseNoOccasion menus: appetizer, main, dessert...
confirmNoMust be true for delete, only after the user agreed
entriesNosave: [{weekday, slot or course, recipe_id or title, label, servings, kind: recipe|needs_recipe|no_cook}]. label = the user's dish name (e.g. "Salad") shown above its recipe link; several entries with the same label/slot/day are one dish with several recipes. Pass back every label from get when re-saving.
weekdayNoadd_entry/set_entry: e.g. "Monday"
entry_idNofill/set_entry/delete_entry: entry id from get
servingsNoServings for the entry
recipe_idNoRecipe id for the entry
visibilityNoshare: private or family (shared with the user's group)
update_listNoadd_entry: true also adds its ingredients to the menu's shopping list
clear_recipeNoset_entry: detach the recipe; the slot goes back to the dish name

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / clear_recipe
      Added value: +{
      +  "description": "set_entry: detach the recipe; the slot goes back to the dish name",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / entries / description
      Previous value: -"save: [{weekday, slot or course, recipe_id or title, servings, kind: recipe|needs_recipe|no_cook}]"New value: +"save: [{weekday, slot or course, recipe_id or title, label, servings, kind: recipe|needs_recipe|no_cook}]. label = the user's dish name (e.g. \"Salad\") shown above its recipe link; several entries with the same label/slot/day are one dish with several recipes. Pass back every label from get when re-saving."
    • addedInput schema / properties / label
      Added value: +{
      +  "description": "add_entry/set_entry: the user's dish name (e.g. \"Salad\") kept above the recipe link; set_entry with only label renames the dish",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations declare destructiveHint=true generically; the description sharpens this into "delete is permanent: ask, then confirm=true," which is exactly the operational guidance an agent needs before an irreversible call. It also discloses the read-only-account write block and the shape of returned data, none of which the annotations carry.

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?

Compressed into four dense sentences with zero filler, front-loading scope, then action grouping, then the destructive-action rule, then return shape. The telegraphic read/write grouping is efficient rather than cryptic.

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?

For an 18-parameter tool with nested entries and no output schema, the description supplies the return shape ({id, title, type, entries} or {menus:[...]}) and the delete confirmation flow, covering the highest-risk gaps. Minor omissions remain — e.g. how share behaves after the call or what copy produces — but the schema covers most field-level detail.

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 the schema already explains every parameter, including action-scoped notes like "save/rename/copy: menu title" and "fill/set_entry/delete_entry: entry id from get." The description adds no parameter-level meaning beyond that, so the 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?

Opens with a specific verb set plus resource: "Create, read, edit, share or delete the user's saved menus," then enumerates the exact action vocabulary (list, get, save, add_entry, fill, set_entry, delete_entry, copy, rename, share, delete). The parenthetical "undated; don't ask for dates" implicitly separates it from the dated planning sibling (plan_menu), so an agent can pick correctly.

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?

Explicitly partitions actions into reads (list, get) and writes, and flags that writes are blocked on read-only accounts — a real precondition. It also states the confirmation protocol for delete and the follow-up rule "Show the whole menu after get/save." It stops short of naming plan_menu as the alternative for dated menus, leaving that inference to the parenthetical.

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